© 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. 72889
    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
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.39
     propOrder
    -0.37
     raisin
    -0.35
     pi
    -0.35
     justin
    -0.34
    ashima
    -0.33
    лимпий
    -0.33
    overrightarrow
    -0.33
    pi
    -0.33
     Raiders
    -0.32
    POSITIVE LOGITS
     ExecuteAsync
    0.95
    Personensuche
    0.91
    LookAnd
    0.91
    ьаж
    0.82
     ویکی‌پدیای
    0.81
    RegistryLite
    0.80
     pinulongan
    0.76
    
    0.75
    ГЛА
    0.75
    +#+#
    0.75
    Activations Density 0.000%

    No Known Activations