© 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. 12176
    Prev
    Next
    INDEX
    Explanations

    involved

    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
     medel
    -0.54
     élevées
    -0.52
    African
    -0.48
     Exacts
    -0.48
     pleinement
    -0.48
     faveur
    -0.48
     étranger
    -0.46
     sû
    -0.45
     lahan
    -0.45
     African
    -0.45
    POSITIVE LOGITS
    ########.
    0.73
    ConstraintMaker
    0.64
    UrlResolution
    0.60
    RetentionPolicy
    0.58
    MENAFN
    0.57
     nahilalakip
    0.57
     Glacier
    0.56
     InputDecoration
    0.55
    ContentAsync
    0.55
    BeginContext
    0.55
    Activations Density 0.053%

    No Known Activations