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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14066
    Prev
    Next
    INDEX
    Explanations

    statistics and play-by-play summaries in sports, with a bias for basketball

    oai_token-act-pair · 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
     itſelf
    -0.88
    ſelf
    -0.80
     purpoſe
    -0.78
    ſelves
    -0.76
     pleaſure
    -0.76
     Reſ
    -0.75
     juſ
    -0.73
    !")
    
    -0.73
     Conſ
    -0.72
     ſta
    -0.72
    POSITIVE LOGITS
     at
    1.29
    @
    0.82
     @
    0.79
    at
    0.71
    AddHtmlAttribute
    0.65
     tại
    0.59
    Vidite
    0.59
     visite
    0.55
    发表于
    0.55
     At
    0.53
    Activations Density 2.118%

    No Known Activations