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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 955
    Prev
    Next
    INDEX
    Explanations

    USA

    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
    usa
    -2.06
    USA
    -1.34
    usas
    -1.30
    uso
    -1.05
     USA
    -0.94
     Usa
    -0.92
    Usa
    -0.91
    usan
    -0.89
     usa
    -0.88
    usen
    -0.81
    POSITIVE LOGITS
     zewnętrzne
    0.59
     délé
    0.56
     transférez
    0.52
     knji
    0.50
    RectangleBorder
    0.50
    UDI
    0.50
    Šaltiniai
    0.50
     meines
    0.48
     الاطلاع
    0.48
     siker
    0.48
    Activations Density 0.317%

    No Known Activations