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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74697
    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
    ⓧ
    -0.79
    jsxFileName
    -0.66
    TypedDataSet
    -0.65
    archiviato
    -0.63
    EndGlobalSection
    -0.63
    ьаж
    -0.62
    isContained
    -0.60
    Lähteet
    -0.59
     betweenstory
    -0.59
     AttributeSet
    -0.59
    POSITIVE LOGITS
     time
    0.56
     cause
    0.54
     volna
    0.47
    ittäin
    0.45
    Time
    0.45
     Lázaro
    0.44
    endiri
    0.44
    ństwo
    0.43
     chain
    0.42
     cauſe
    0.42
    Activations Density 0.000%

    No Known Activations