© 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. 1-CLT-HP
    7. 12189
    Prev
    Next
    INDEX
    Explanations

    news/blog article snippets

    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
    owan
    -0.85
    BorderFactory
    -0.50
     Nazar
    -0.49
    UrlResolution
    -0.49
    GetMapping
    -0.47
     DbType
    -0.46
     Verdi
    -0.45
    acea
    -0.45
    GenerationType
    -0.44
    PMailer
    -0.44
    POSITIVE LOGITS
     propOrder
    0.69
     ModelExpression
    0.66
     pediatrician
    0.60
    ISupport
    0.57
    ptonshire
    0.56
     defaultstate
    0.56
    semantics
    0.54
    writeField
    0.53
     sometime
    0.50
    Hauptartikel
    0.50
    Activations Density 0.005%

    No Known Activations