© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Weight-Sparse Transformers
    5. CircuitGPT-Python
    7. MLP
    9. 2-MLP
    11. 7716
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    the identifier sum (negative activations)

    python-code · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 256 tokens each
    Dataset (Dashboard)
    neuronpedia/python-code-simplified
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ize
    -0.07
    ilities
    -0.06
    iz
    -0.06
    gth
    -0.05
    ized
    -0.05
    ulate
    -0.05
    ulation
    -0.05
    ul
    -0.04
    ise
    -0.04
    tail
    -0.04
    POSITIVE LOGITS
    3
    0.03
    2
    0.03
     **
    0.03
    4
    0.03
    1
    0.03
    6
    0.03
    x
    0.03
    di
    0.02
    5
    0.02
    7
    0.02
    Activations Density 73.588%

    No Known Activations