© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2850
    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
    SaveChangesAsync
    -0.68
     திரு
    -0.60
     NSCoder
    -0.60
     ***/
    -0.58
    πάρχ
    -0.57
     sheaves
    -0.57
    gable
    -0.56
     incomplète
    -0.56
     StatefulWidget
    -0.56
    waits
    -0.54
    POSITIVE LOGITS
    ://"
    0.49
    出版年
    0.49
    esModule
    0.47
    fortawesome
    0.47
    GOTREF
    0.46
     Gual
    0.45
    hoga
    0.45
    "]();
    0.43
     _
    0.42
    NewUrlParser
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.