© 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. 5340
    Prev
    Next
    INDEX
    Explanations

    forEach

    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
    DockStyle
    -1.09
     فريبيس
    -1.06
     tartalomajánló
    -1.03
    IsContent
    -1.00
    aarrggbb
    -0.94
    ArgsConstructor
    -0.93
    setVerticalGroup
    -0.90
    LookAnd
    -0.90
    ViewImports
    -0.87
    UnusedPrivate
    -0.86
    POSITIVE LOGITS
     רבה
    0.42
     ním
    0.34
     posled
    0.32
     ně
    0.32
     cland
    0.30
    ุต
    0.30
     siang
    0.30
     الرحمن
    0.29
     esteve
    0.29
    といって
    0.29
    Activations Density 0.000%

    No Known Activations