© 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. 71797
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    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
    setVerticalGroup
    -0.82
    StoryboardSegue
    -0.77
    ſelf
    -0.73
     myſelf
    -0.71
     poffe
    -0.70
    IsContent
    -0.69
     houſe
    -0.69
     Theſe
    -0.68
     itſelf
    -0.68
     Efq
    -0.67
    POSITIVE LOGITS
    httphttps
    0.46
    점
    0.42
    ULL
    0.41
    rawDesc
    0.40
     externi
    0.39
    ull
    0.39
    omonas
    0.38
     Macau
    0.38
    riques
    0.37
    žev
    0.36
    Activations Density 0.006%

    No Known Activations