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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5930
    Prev
    Next
    INDEX
    Explanations

    the phrase "kind of"

    oai_token-act-pair · gemini-2.0-flash

    phrases starting with "kind of"

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

    kind

    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
    ⓧ
    -0.75
    inSlope
    -0.65
    tabilis
    -0.64
    UnsafeEnabled
    -0.63
    ArgsConstructor
    -0.60
    webElementGuid
    -0.60
    󠁧
    -0.58
    🏼
    -0.58
    URIComponent
    -0.57
     وتسجيلات
    -0.57
    POSITIVE LOGITS
     of
    0.97
    ของ
    0.62
    -------------</
    0.56
     EconPapers
    0.56
    ########.
    0.56
     encuent
    0.50
     StatefulWidget
    0.48
     mergeFrom
    0.48
     của
    0.48
     line
    0.44
    Activations Density 1.670%

    No Known Activations