© 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. 72238
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     ivelany
    -0.57
    ERSHIP
    -0.56
    útbol
    -0.55
    ponses
    -0.54
    esModule
    -0.54
    Nguồn
    -0.54
    latego
    -0.54
    utebol
    -0.53
    BufferException
    -0.52
    ubourg
    -0.52
    POSITIVE LOGITS
     Preferencias
    0.63
    jspx
    0.60
    يميديا
    0.53
    migrationBuilder
    0.52
    DriverManager
    0.49
    mybatisplus
    0.47
    таратура
    0.47
    viewDidLoad
    0.46
    BaseAdapter
    0.45
     liệu
    0.44
    Activations Density 0.002%

    No Known Activations