© 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. 71942
    Prev
    Next
    INDEX
    Explanations

    my

    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
    VIAF
    -0.65
    بوابة
    -0.59
    Slf
    -0.56
    LabelTagHelper
    -0.55
     Folding
    -0.55
     Clerical
    -0.54
     Grav
    -0.54
    tréal
    -0.54
     arşivlendi
    -0.54
     فريبيس
    -0.53
    POSITIVE LOGITS
     EconPapers
    0.61
     getItemId
    0.59
    cop
    0.53
    mybatisplus
    0.48
    xo
    0.46
     beginnetje
    0.46
    iasis
    0.42
    aop
    0.42
    oredCriteria
    0.41
    opcao
    0.41
    Activations Density 0.007%

    No Known Activations