© 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. Gemma-2-2B
    5. 5-CLT-HP
    7. 4603
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ussis
    -0.51
     rivi
    -0.49
     "..\..\
    -0.47
     unknownFields
    -0.47
     ویکی‌پدیای
    -0.47
    ظر
    -0.47
    Bathrooms
    -0.46
     Morty
    -0.46
    FieldBuilder
    -0.46
     figs
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.60
    CÁ
    0.59
     resourceCulture
    0.59
    انجليز
    0.59
    idän
    0.57
    cería
    0.56
     ExecuteAsync
    0.55
    NUMX
    0.54
    TemporalType
    0.54
    MigrationBuilder
    0.54
    Activations Density 0.018%

    No Known Activations