© 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. 92379
    Prev
    Next
    INDEX
    Explanations

    Mathematical/programmatic notation

    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
    ,
    -0.57
     point
    -0.56
    FunctionFlags
    -0.54
    .
    -0.54
     for
    -0.54
     of
    -0.52
     with
    -0.51
     at
    -0.51
     warning
    -0.50
     grosso
    -0.49
    POSITIVE LOGITS
    KommentareTeilen
    0.70
     Baillargeon
    0.69
    }{*}{
    0.62
    PreferredItem
    0.58
     فريبيس
    0.57
    Personensuche
    0.56
    存于互联网档案馆
    0.54
    saraba
    0.54
    nEnter
    0.54
     betweenstory
    0.54
    Activations Density 0.011%

    No Known Activations