© 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. 2309
    Prev
    Next
    INDEX
    Explanations

    way

    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
    RegressionTest
    -0.88
    RenderAtEndOf
    -0.87
     ویکی‌پدی
    -0.84
    AntiForgeryToken
    -0.79
    LookAnd
    -0.79
    ThroughAttribute
    -0.77
    Хьажоргаш
    -0.74
    Vidite
    -0.68
    enumii
    -0.66
    XmlEnum
    -0.66
    POSITIVE LOGITS
     of
    0.77
    paws
    0.46
    !
    0.46
     keper
    0.43
    walls
    0.43
     or
    0.42
    lungs
    0.41
    localctx
    0.41
    titur
    0.40
     komende
    0.38
    Activations Density 0.001%

    No Known Activations