© 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. 0-CLT-HP
    7. 38430
    Prev
    Next
    INDEX
    Explanations

    sport

    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
     sport
    -1.36
     sports
    -1.28
    sport
    -1.28
     sporting
    -1.10
     Sport
    -1.06
    sports
    -1.05
     Sports
    -1.03
    Sport
    -0.99
    Sports
    -0.92
     SPORT
    -0.88
    POSITIVE LOGITS
     الحره
    0.95
    ंदीखरीदारी
    0.83
    Cyfeiriadau
    0.72
     كومونز
    0.71
     Efq
    0.69
    IUrlHelper
    0.69
     تضيفلها
    0.68
     actionMode
    0.68
     Jefus
    0.68
    humidité
    0.67
    Activations Density 1.015%

    No Known Activations