© 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. 4-CLT-HP
    7. 2553
    Prev
    Next
    INDEX
    Explanations

    Chinese last names

    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
    APORE
    -0.50
    MENAFN
    -0.44
     Мексичка
    -0.44
    MigrationBuilder
    -0.43
     referrerpolicy
    -0.40
     Baillargeon
    -0.35
    witz
    -0.35
    oplayer
    -0.33
    ttemberg
    -0.33
     Italijani
    -0.32
    POSITIVE LOGITS
    ็จ
    0.69
    aronder
    0.69
    ouwd
    0.65
    GEBURTSDATUM
    0.62
    #+#
    0.62
    TestingModule
    0.61
    */;
    0.60
     độ
    0.60
    anstalt
    0.60
     nemlig
    0.60
    Activations Density 0.002%

    No Known Activations