Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11173
    Prev
    Next
    INDEX
    Explanations

    names and official titles, especially in the context of Edo State government

    oai_token-act-pair · gemini-2.0-flash

    programming and technical terms

    np_token-act-pair-logits · gpt-4o-mini

    news/reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.56
     WaitForSeconds
    -0.53
     Zoll
    -0.49
     Wikispecies
    -0.48
    toCharArray
    -0.47
    leuchte
    -0.46
     Apos
    -0.45
     endothe
    -0.45
    植え
    -0.44
    rrggbb
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.83
    TagMode
    0.78
     архивлан
    0.64
    ⓧ
    0.59
    Jeografia
    0.57
    VersionUID
    0.57
    Produzione
    0.56
    umerable
    0.56
     nemen
    0.55
    دانشنامهٔ
    0.55
    Activations Density 4.943%

    No Known Activations