© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-CLT-HP
    4. 1587
    Prev
    Next
    INDEX
    Explanations

    code and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.67
     Vikipedi
    -0.59
    tvguidetime
    -0.59
    UnitTesting
    -0.58
     proposito
    -0.56
    AutoScaleMode
    -0.55
     larmes
    -0.55
     miei
    -0.54
     säll
    -0.54
     propOrder
    -0.54
    POSITIVE LOGITS
     the
    0.81
    клопе
    0.77
     following
    0.64
     with
    0.60
     from
    0.59
     in
    0.59
     ͡°)
    0.57
     ̄)
    0.57
    ſelf
    0.57
    />";
    0.56
    Activations Density 0.001%

    No Known Activations