© 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. 0-CLT-HP
    7. 42500
    Prev
    Next
    INDEX
    Explanations

    devote

    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
     ModelExpression
    -0.84
    Erreferentziak
    -0.75
    HasBeenSet
    -0.74
     مشين
    -0.73
     للمعارف
    -0.71
    tagHelperRunner
    -0.70
    DeleteBehavior
    -0.70
    writeFieldEnd
    -0.67
    mobileqq
    -0.67
    teness
    -0.66
    POSITIVE LOGITS
    stdc
    0.44
    apas
    0.44
     AP
    0.43
     Must
    0.43
     Taken
    0.42
    Stab
    0.42
     esist
    0.42
    COMMENTS
    0.41
    Results
    0.41
    focusable
    0.41
    Activations Density 0.161%

    No Known Activations