© 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. 5-CLT-HP
    7. 95254
    Prev
    Next
    INDEX
    Explanations

    healthcare professionals

    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
     Италијани
    -0.73
    enumii
    -0.72
    <bos>
    -0.71
    Personensuche
    -0.71
     Paglinawan
    -0.70
    }{*}{}
    -0.67
    الحياه
    -0.66
    PhysRev
    -0.66
     للمعارف
    -0.63
     <<<<<<<<<<<<<<
    -0.62
    POSITIVE LOGITS
    Executives
    0.45
     âgé
    0.44
     أش
    0.44
     poda
    0.44
    combo
    0.43
     Cio
    0.42
    shadow
    0.42
    님
    0.41
     appeler
    0.41
    rotto
    0.41
    Activations Density 0.003%

    No Known Activations