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. 0-CLT-HP
    4. 40898
    Prev
    Next
    INDEX
    Explanations

    sports win

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.07
    gameserver
    -1.02
     ſind
    -1.02
     pleaſure
    -1.02
     doInBackground
    -1.00
    MigrationBuilder
    -0.98
    parsedMessage
    -0.97
     purpoſe
    -0.97
     itſelf
    -0.96
     win
    -0.94
    POSITIVE LOGITS
     of
    0.68
    no
    0.56
    n
    0.56
    na
    0.55
    tura
    0.54
    ng
    0.49
    ter
    0.49
    tr
    0.48
    .
    0.48
    nan
    0.48
    Activations Density 0.108%

    No Known Activations