© 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. 5243
    Prev
    Next
    INDEX
    Explanations

    caris

    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
    تقاوى
    -0.49
     vindo
    -0.48
     Cessna
    -0.47
     accanto
    -0.46
     Etrus
    -0.46
    pexpr
    -0.46
    ruptedException
    -0.44
     flattered
    -0.44
    webElement
    -0.44
    oció
    -0.43
    POSITIVE LOGITS
     виправивши
    0.66
     Preferencias
    0.66
    '],'
    0.57
    oredCriteria
    0.57
     continúas
    0.56
    chige
    0.54
    ;=
    0.53
    $,
    0.53
    ;",
    0.53
     _,
    0.52
    Activations Density 0.042%

    No Known Activations