© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3029
    Prev
    Next
    INDEX
    Explanations

    sports

    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
    $_['
    -0.49
     gez
    -0.45
    WebControls
    -0.43
    лям
    -0.40
    ilty
    -0.40
    udes
    -0.39
    кта
    -0.39
    థ
    -0.39
     Kette
    -0.38
    ьаж
    -0.38
    POSITIVE LOGITS
     coaches
    0.73
     coach
    0.68
     players
    0.64
     playoff
    0.63
     player
    0.63
     playoffs
    0.62
     trades
    0.61
     scouts
    0.60
     stadiums
    0.59
     offseason
    0.59
    Activations Density 0.005%

    No Known Activations