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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16334
    Prev
    Next
    INDEX
    Explanations

    the word "traditional" and words associated with it, regardless of context

    oai_token-act-pair · gemini-2.0-flash

    Traditional

    np_token-act-pair-logits · gemini-2.0-flash

    traditional

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     typelib
    -0.51
    tradition
    -0.51
     المعيارى
    -0.50
    //
    -0.49
    Tradition
    -0.48
    ValueStyle
    -0.48
     Tradition
    -0.46
    ubation
    -0.46
    istema
    -0.46
    Tembelea
    -0.46
    POSITIVE LOGITS
    nasse
    0.63
    ChildScrollView
    0.62
    TemporalType
    0.56
    TargetException
    0.56
    crollView
    0.56
    gonic
    0.54
    rimidine
    0.54
    Higgins
    0.52
    fficio
    0.52
    +:+
    0.51
    Activations Density 1.056%

    No Known Activations