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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42218
    Prev
    Next
    INDEX
    Explanations

    sports competition

    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
     duel
    -1.59
     Duel
    -1.11
     duels
    -1.04
    Duel
    -0.91
    duel
    -0.89
    Vidite
    -0.81
     dual
    -0.79
     JpaRepository
    -0.79
     surla
    -0.78
    dual
    -0.73
    POSITIVE LOGITS
    ants
    0.60
    istic
    0.57
    ists
    0.54
    lists
    0.51
    ins
    0.49
    llllllll
    0.47
    iste
    0.46
    aries
    0.45
    isti
    0.45
    istics
    0.45
    Activations Density 0.306%

    No Known Activations