© 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. 0-CLT-HP
    7. 95543
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    JspWriter
    -0.94
     المعيارى
    -0.81
    matchCondition
    -0.75
     Signalez
    -0.75
    بوابة
    -0.68
    RectangleBorder
    -0.66
    archiviato
    -0.66
    </caption>
    -0.64
     فريبيس
    -0.64
     Chwiliwch
    -0.63
    POSITIVE LOGITS
    lje
    0.46
    utzer
    0.45
    ALTH
    0.44
    wole
    0.44
     complete
    0.43
     défaut
    0.43
     Cosmo
    0.43
     Drit
    0.42
    قایناق‌لار
    0.42
    cesso
    0.42
    Activations Density 1.675%

    No Known Activations