© 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. 1-CLT-HP
    7. 13186
    Prev
    Next
    INDEX
    Explanations

    su

    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
    ;->
    -0.47
    RetentionPolicy
    -0.47
    nationality
    -0.47
    NotNull
    -0.46
     насељу
    -0.46
     Sen
    -0.44
    DetailActivity
    -0.43
    Istorija
    -0.43
    beri
    -0.42
    ashe
    -0.42
    POSITIVE LOGITS
    KommentareTeilen
    0.63
    mobileqq
    0.52
    setVerticalGroup
    0.50
    Condol
    0.50
    UnusedPrivate
    0.49
    bibliography
    0.48
     consultato
    0.48
    genommen
    0.48
    Bibliographie
    0.48
    oming
    0.47
    Activations Density 0.010%

    No Known Activations