© 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. 4-CLT-HP
    7. 401
    Prev
    Next
    INDEX
    Explanations

    numerals

    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
    WebElementEntity
    -0.58
    PyExc
    -0.53
    dfunding
    -0.50
    glades
    -0.50
    jspx
    -0.50
    forRoot
    -0.50
    ycz
    -0.49
    gradable
    -0.49
     plads
    -0.48
    \|^{
    -0.47
    POSITIVE LOGITS
     незавершена
    0.58
     كومونز
    0.56
    .
    0.52
     in
    0.52
    complexContent
    0.52
     typelib
    0.52
     including
    0.51
     then
    0.51
     scoper
    0.51
     ControllerBase
    0.51
    Activations Density 0.023%

    No Known Activations