© 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. 43345
    Prev
    Next
    INDEX
    Explanations

    nationalities/locations

    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
    quartered
    -0.77
    peed
    -0.70
    InputBorder
    -0.69
    complexContent
    -0.69
     resident
    -0.68
    Билгалдахарш
    -0.65
     élas
    -0.64
     mères
    -0.64
    Resident
    -0.62
    residence
    -0.62
    POSITIVE LOGITS
     honours
    0.62
     spurs
    0.57
     Carina
    0.56
     toast
    0.52
     Aene
    0.52
    rous
    0.51
     Uranus
    0.51
     anſ
    0.51
     itſelf
    0.51
     ſta
    0.50
    Activations Density 0.042%

    No Known Activations