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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10131
    Prev
    Next
    INDEX
    Explanations

    instances of the word "talk" or "talking"

    oai_token-act-pair · gemini-2.0-flash

    talk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_19/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
     uſe
    -0.68
     Eſ
    -0.65
     Monfieur
    -0.62
     uſ
    -0.60
     fevere
    -0.60
     ſeveral
    -0.60
     ſtate
    -0.58
     RouterModule
    -0.57
     poffible
    -0.57
     raiſ
    -0.57
    POSITIVE LOGITS
     ostavi
    0.60
    windowFixed
    0.56
    цездатний
    0.52
    లాలు
    0.52
     about
    0.51
    Попис
    0.51
     متعلقه
    0.48
    BeginContext
    0.45
     Valent
    0.45
    UnknownFields
    0.45
    Activations Density 1.819%

    No Known Activations