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. 5916
    Prev
    Next
    INDEX
    Explanations

    mentions of North Carolina cities, especially when preceded by "such as."

    oai_token-act-pair · gemini-2.0-flash

    technical terms and code-related phrases

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

    NC locations and news articles

    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
     Jefus
    -0.71
     myſelf
    -0.68
     Theſe
    -0.67
     Monfieur
    -0.65
     Conſ
    -0.65
     alſo
    -0.64
     ſeveral
    -0.63
     Efq
    -0.62
     ſtate
    -0.62
     purpoſe
    -0.61
    POSITIVE LOGITS
    quim
    0.54
     jabón
    0.52
    ItemBackground
    0.50
    tvguidetime
    0.49
    tagHelperRunner
    0.48
    يكب
    0.47
    fxml
    0.45
    Parcelize
    0.44
    aarrggbb
    0.44
    ="@+
    0.44
    Activations Density 1.297%

    No Known Activations