© 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. 7832
    Prev
    Next
    INDEX
    Circuit Sparsity
    No connected neurons data available
    Explanations

    match for `pack`

    python-code · gemini-2.5-flash-lite

    'activation' keyword argument (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
    ates
    -0.05
    ize
    -0.05
    param
    -0.05
    },↵
    -0.04
    args
    -0.04
     the
    -0.04
    lose
    -0.04
    ating
    -0.04
     Par
    -0.03
    ate
    -0.03
    POSITIVE LOGITS
     minimum
    0.06
    jkstra
    0.06
    ~
    0.05
    ]['
    0.05
    (min
    0.05
     min
    0.04
    min
    0.04
    _min
    0.04
     {'
    0.04
     max
    0.04
    Activations Density 100.000%

    No Known Activations