© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45316
    Prev
    Next
    INDEX
    Explanations

    more

    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
     more
    -2.11
    more
    -1.52
     lebih
    -1.31
    More
    -1.30
     mehr
    -1.30
     более
    -1.30
     più
    -1.27
     más
    -1.24
    更多
    -1.20
     More
    -1.16
    POSITIVE LOGITS
     than
    0.96
     THAN
    0.82
     ExecuteAsync
    0.76
    WebElementEntity
    0.75
     of
    0.73
     nakalista
    0.72
     importantly
    0.71
    tagHelperRunner
    0.69
    ModelAdmin
    0.68
    InSection
    0.68
    Activations Density 0.211%

    No Known Activations