© 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. 4-CLT-HP
    7. 4391
    Prev
    Next
    INDEX
    Explanations

    the

    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
     scraped
    -0.79
     scrape
    -0.73
    MigrationBuilder
    -0.73
     scraping
    -0.72
     skimming
    -0.69
     shaved
    -0.63
     skimmed
    -0.63
     skim
    -0.62
     exclusions
    -0.62
     يتيمه
    -0.61
    POSITIVE LOGITS
    AddHtmlAttribute
    0.66
    ScopeManager
    0.53
     विश्वसनीयता
    0.46
     kasarigan
    0.46
     colorés
    0.45
    thâu
    0.42
    دانشنامهٔ
    0.42
     plastiques
    0.42
    itier
    0.42
    Välislingid
    0.41
    Activations Density 0.002%

    No Known Activations