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. 16330
    Prev
    Next
    INDEX
    Explanations

    of

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

    of

    np_max-act-logits · gemini-2.0-flash

    the word "of" and nearby articles

    oai_token-act-pair · 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
     متعلقه
    -0.87
    )");
    
    -0.78
    )")
    -0.74
    )}</
    -0.74
     AssemblyCulture
    -0.73
    CloseOperation
    -0.73
    ГЛА
    -0.71
     autorytatywna
    -0.71
    %")
    -0.69
    +#+#
    -0.68
    POSITIVE LOGITS
    /**
    0.61
    MethodManager
    0.54
     Top
    0.40
    dagangan
    0.38
    DIPSETTING
    0.37
     DbType
    0.36
    l
    0.36
     totalt
    0.36
    ellees
    0.35
    PullParser
    0.35
    Activations Density 0.195%

    No Known Activations