© 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. 94738
    Prev
    Next
    INDEX
    Explanations

    zilla

    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
    hance
    -0.53
     showing
    -0.52
     AssemblyCulture
    -0.49
    رم
    -0.46
    דיה
    -0.46
    keyColumn
    -0.46
    tojas
    -0.45
    zilla
    -0.45
     представ
    -0.45
    ãy
    -0.45
    POSITIVE LOGITS
    noinspection
    0.71
     ujednoznacz
    0.70
    TagHelper
    0.69
     CreateTagHelper
    0.68
     MonoBehaviour
    0.68
    ViewImports
    0.67
    queryInterface
    0.66
     ویکی‌آمباردا
    0.65
    UVWXYZ
    0.65
    #+#
    0.63
    Activations Density 2.262%

    No Known Activations