© 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. 73078
    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
    MemoryWarning
    -0.57
    migrationBuilder
    -0.53
     uParam
    -0.50
    maxcdn
    -0.47
    руппа
    -0.47
     تانيه
    -0.47
    providedIn
    -0.46
    ADVERT
    -0.46
    MENAFN
    -0.46
    hasMoreElements
    -0.45
    POSITIVE LOGITS
    basicConfig
    0.59
     Ferdin
    0.52
     ویکی‌پدی
    0.50
    :^{
    0.49
    rillation
    0.47
    UnknownFieldSet
    0.47
     getRule
    0.46
    ormais
    0.46
    Risultati
    0.45
    WriteLiteral
    0.45
    Activations Density 0.006%

    No Known Activations