© 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. 20-CLT-HP
    7. 76418
    Prev
    Next
    INDEX
    Explanations

    technical/uncommon information

    np_max-act-logits · 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
    EDEFAULT
    -0.52
    PullParser
    -0.46
    verwijspagina
    -0.45
    unitOfWork
    -0.44
    Rüyada
    -0.44
     Abp
    -0.43
    XtraGrid
    -0.41
    +#+#
    -0.41
     Louisville
    -0.40
    ärä
    -0.40
    POSITIVE LOGITS
    WebServlet
    0.67
     draught
    0.62
    MENAFN
    0.61
     unknownFields
    0.60
    enumii
    0.58
    inafter
    0.57
    favourable
    0.57
     ©️
    0.57
     fieldNum
    0.56
    стота
    0.55
    Activations Density 0.000%

    No Known Activations