© 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. 3001
    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
    OGND
    -0.80
    ControllerAdvice
    -0.76
     BoxDecoration
    -0.70
    archiviato
    -0.67
     SQLAlchemy
    -0.67
    errHandler
    -0.65
     blessés
    -0.64
     dentaire
    -0.64
     useAuth
    -0.63
     Picchu
    -0.61
    POSITIVE LOGITS
    [](
    0.53
     insert
    0.52
    спу
    0.47
     inserts
    0.47
     Insert
    0.46
    kmale
    0.46
    »,
    0.45
    Formats
    0.44
     null
    0.43
    TypeInfo
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.