© 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. 1-CLT-HP
    7. 10406
    Prev
    Next
    INDEX
    Explanations

    eto

    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
    mmons
    -0.61
    astes
    -0.54
    دانشنامهٔ
    -0.53
    ⓧ
    -0.52
    tagHelperRunner
    -0.52
    InjectAttribute
    -0.52
    ReusableCell
    -0.51
    المناصب
    -0.50
    ISupport
    -0.50
    lette
    -0.48
    POSITIVE LOGITS
     informée
    0.57
     disambiguazione
    0.56
    izontal
    0.54
    phous
    0.54
    KommentareTeilen
    0.52
    Odkazy
    0.52
     unbalanced
    0.52
    LikeLike
    0.52
    yta
    0.51
    AddHtmlAttribute
    0.51
    Activations Density 0.030%

    No Known Activations