© 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. 1-CLT-HP
    7. 10116
    Prev
    Next
    INDEX
    Explanations

    course

    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
    GEBURTSDATUM
    -0.73
    TintMode
    -0.60
    nestjs
    -0.56
    Alike
    -0.56
    Viki
    -0.56
     autorytatywna
    -0.54
    ExtendWith
    -0.54
     Ehre
    -0.53
    ubar
    -0.52
     propOrder
    -0.52
    POSITIVE LOGITS
    principalColumn
    0.53
     for
    0.53
    itinéraire
    0.52
    ValueStyle
    0.51
    出版年
    0.48
     nahilalakip
    0.48
     forState
    0.47
    ंदीखरीदारी
    0.47
     AppModule
    0.47
     AssemblyCulture
    0.46
    Activations Density 0.159%

    No Known Activations