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. 11171
    Prev
    Next
    INDEX
    Explanations

    phrases related to diversity, traditions and religious studies

    oai_token-act-pair · gemini-2.0-flash

    prefixes related to "tradition"

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

    cultures and traditions

    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
    IVEREF
    -0.84
    DockStyle
    -0.79
    ViewImports
    -0.77
    ngdoc
    -0.73
     виправивши
    -0.71
     kaarangay
    -0.68
     chi̍t
    -0.68
    AddHtmlAttribute
    -0.67
    tagHelperRunner
    -0.65
    GOTREF
    -0.65
    POSITIVE LOGITS
    tra
    0.60
    antin
    0.55
    anti
    0.52
     Tra
    0.51
    Tra
    0.50
     tra
    0.49
     cross
    0.48
    etra
    0.48
     тра
    0.47
    itra
    0.46
    Activations Density 1.302%

    No Known Activations