Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 10991
    Prev
    Next
    INDEX
    Explanations

    enter

    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
     enter
    -0.53
    一等
    -0.52
     ge
    -0.49
     pre
    -0.45
     Civil
    -0.43
    iency
    -0.43
     wir
    -0.43
     (
    -0.43
     tick
    -0.43
     Ge
    -0.42
    POSITIVE LOGITS
    afficheront
    0.81
     Wikimedijinoj
    0.80
    Personendaten
    0.77
    EndGlobalSection
    0.74
    CloseOperation
    0.71
     للمعارف
    0.70
     дописавши
    0.68
    SharedDtor
    0.68
    يكب
    0.66
    AccessorTable
    0.65
    Activations Density 0.102%

    No Known Activations