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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16279
    Prev
    Next
    INDEX
    Explanations

    various syntax elements of several different programming languages

    oai_token-act-pair · gemini-2.0-flash

    Code context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
    krä
    -0.45
    וא
    -0.45
     Der
    -0.44
     hol
    -0.41
     Borg
    -0.40
     sty
    -0.40
     Im
    -0.39
    Iw
    -0.39
     OkHttpClient
    -0.39
    HttpEntity
    -0.39
    POSITIVE LOGITS
    VersionUID
    0.90
     <>",
    0.89
     يتيمه
    0.82
     NSCoder
    0.81
     Houſe
    0.80
    Vidite
    0.80
     للاسماء
    0.77
     مرئيه
    0.75
     noDo
    0.75
     XNUMX
    0.73
    Activations Density 0.470%

    No Known Activations