# Hidden layer gradients are more complex due to chain rule
print("Hidden layer gradient breakdown:")
print("dz1 = (dz2 @ W2.T) * sigmoid_derivative(z1)")

# Step by step
error_propagated = dz2 @ W2.T  # Propagate error backwards
print(f"Error propagated shape: {error_propagated.shape}")
print(f"This spreads output error to each hidden neuron")

hidden_sigmoid_grad = sigmoid_derivative(z1)  # Local gradient
print(f"Hidden sigmoid gradient shape: {hidden_sigmoid_grad.shape}")

dz1_step = error_propagated * hidden_sigmoid_grad  # Final gradient
print(f"Combined hidden gradient (dz1) shape: {dz1_step.shape}")