© 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. 20-CLT-HP
    7. 76081
    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
    </caption>
    -0.55
    IGraphics
    -0.52
    nasa
    -0.48
    RETURNS
    -0.45
    Spacer
    -0.45
    塁
    -0.44
     CAV
    -0.44
    ARGV
    -0.43
    vanna
    -0.43
     fumble
    -0.42
    POSITIVE LOGITS
    Portály
    0.71
    ftagPool
    0.68
     Normdatei
    0.65
    ,:);
    0.62
     فريبيس
    0.57
    __':
    0.56
    iseerd
    0.56
     tartalomajánló
    0.55
    Искәрмәләр
    0.55
     intStringLen
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.