© 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. 20-CLT-HP
    7. 72746
    Prev
    Next
    INDEX
    Explanations

    Olympics

    np_max-act-logits · 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
    +#+#
    -0.90
     olympique
    -0.79
     BoxDecoration
    -0.76
     olympic
    -0.74
     Taktlose
    -0.73
     nakalista
    -0.71
    olymp
    -0.71
     cherchés
    -0.71
    Olympic
    -0.70
     kaarangay
    -0.70
    POSITIVE LOGITS
     Res
    0.52
    Res
    0.49
     res
    0.48
    res
    0.45
    resar
    0.45
     Church
    0.40
     rez
    0.40
     
    0.39
    DataPropertyName
    0.39
    expandindo
    0.38
    Activations Density 0.006%

    No Known Activations