© 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. 5-CLT-HP
    4. 96209
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    rosia
    -0.47
     Ein
    -0.47
    免
    -0.46
    raf
    -0.44
     ves
    -0.43
    dige
    -0.42
    <bos>
    -0.42
    Provincial
    -0.41
     Patel
    -0.41
    PriorityQueue
    -0.40
    POSITIVE LOGITS
    :✨
    0.78
    expandindo
    0.77
    IsMutable
    0.75
    SourceChecksum
    0.71
    دانشنامهٔ
    0.69
     HasFactory
    0.67
     مشين
    0.60
    Награды
    0.59
    cinnati
    0.59
    IntoConstraints
    0.58
    Activations Density 0.017%

    No Known Activations