© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 11508
    Prev
    Next
    INDEX
    Explanations

    factors

    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
     мәкал
    -0.53
     contextLoads
    -0.52
     domo
    -0.51
    extAlignment
    -0.51
     HasFactory
    -0.50
    IBAction
    -0.49
    قایناقلار
    -0.48
    $^{-
    -0.48
     كومونز
    -0.48
    脚注の使い方
    -0.47
    POSITIVE LOGITS
    <bos>
    0.68
     like
    0.58
    isPresent
    0.55
     intersecting
    0.55
     widen
    0.55
    pośred
    0.54
    mybatisplus
    0.53
    psilon
    0.52
     that
    0.52
    RowCount
    0.52
    Activations Density 0.004%

    No Known Activations