© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 16249
    Prev
    Next
    INDEX
    Explanations

    ci

    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
    Negative Logits
    ci
    -0.88
     تانيه
    -0.77
     مشين
    -0.66
     defaultstate
    -0.65
     Mention
    -0.63
     AssemblyCulture
    -0.63
     mention
    -0.62
    참고
    -0.60
    extAlignment
    -0.60
    Slf
    -0.57
    POSITIVE LOGITS
    ed
    0.96
    er
    0.86
    ers
    0.65
    s
    0.62
    ement
    0.52
    y
    0.52
    ER
    0.51
    ED
    0.50
    ered
    0.50
    rode
    0.48
    Activations Density 0.056%

    No Known Activations