© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3387
    Prev
    Next
    INDEX
    Explanations

    economic

    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
     OFDb
    -0.58
    tagHelperRunner
    -0.57
    thenes
    -0.56
    +#+#
    -0.54
     Din
    -0.54
    motherapy
    -0.52
    Dich
    -0.52
    udin
    -0.52
    هن
    -0.50
     kaarangay
    -0.50
    POSITIVE LOGITS
     MainAxisSize
    0.71
    enderror
    0.58
    glie
    0.56
    ագրություններ
    0.52
    jsxFileName
    0.51
    __*/
    0.50
    PMailer
    0.50
    énario
    0.49
    formik
    0.49
     Seeder
    0.49
    Activations Density 0.003%

    No Known Activations