© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91098
    Prev
    Next
    INDEX
    Explanations

    came

    np_max-act · gemini-2.0-flash
    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
     فريبيس
    -0.88
    XmlAccessType
    -0.79
    存于互联网档案馆
    -0.60
     saites
    -0.60
     ModelExpression
    -0.59
    parsedMessage
    -0.59
    câ
    -0.59
     Credits
    -0.57
     arose
    -0.57
     חיצוניים
    -0.57
    POSITIVE LOGITS
    <bos>
    0.56
     not
    0.48
    awaiter
    0.47
     at
    0.45
    pushFollow
    0.43
     also
    0.41
     often
    0.40
    piring
    0.40
     now
    0.39
    ImageContext
    0.39
    Activations Density 0.047%

    No Known Activations