© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93259
    Prev
    Next
    INDEX
    Explanations

    athletics

    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
     Audiodateien
    -0.73
     practising
    -0.63
     proficiency
    -0.62
    manship
    -0.60
    Malley
    -0.59
    trained
    -0.59
    Trained
    -0.59
     Sing
    -0.58
    objective
    -0.57
     practised
    -0.55
    POSITIVE LOGITS
     pageContext
    0.57
    bindParam
    0.55
     counter
    0.49
    してきました
    0.49
    Usual
    0.48
     chinese
    0.48
     Erişim
    0.47
     semicolon
    0.47
     POOR
    0.47
     doInBackground
    0.47
    Activations Density 0.066%

    No Known Activations