© 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. 20-CLT-HP
    7. 71669
    Prev
    Next
    INDEX
    Explanations

    2

    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
     '\\;'
    -0.74
     defaultstate
    -0.68
    WebElementEntity
    -0.59
    êques
    -0.56
    клопе
    -0.55
     useEffect
    -0.55
    imedes
    -0.54
    iprot
    -0.54
     ligiloj
    -0.53
    }}}$
    -0.52
    POSITIVE LOGITS
     AspNetCore
    0.55
    Datuak
    0.53
     Field
    0.46
     zirconia
    0.44
     Waray
    0.42
     Catto
    0.41
     Bands
    0.40
    readdir
    0.40
    mapStateToProps
    0.40
     تضيفلها
    0.40
    Activations Density 0.004%

    No Known Activations