© 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. 0-CLT-HP
    7. 90895
    Prev
    Next
    INDEX
    Explanations

    sports/professional contexts

    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
    indd
    -0.62
    millimeters
    -0.56
     belliger
    -0.56
    mybatisplus
    -0.55
     BeautifulSoup
    -0.55
    endphp
    -0.54
    cestry
    -0.53
    strokes
    -0.53
     singles
    -0.53
     wikihow
    -0.53
    POSITIVE LOGITS
    holdet
    0.68
     graphiques
    0.60
     mères
    0.60
     keskus
    0.59
     plais
    0.59
     commerciaux
    0.56
     szár
    0.56
     nakalista
    0.56
     partag
    0.56
     forbindelse
    0.56
    Activations Density 0.130%

    No Known Activations