© 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. 0-CLT-HP
    7. 38715
    Prev
    Next
    INDEX
    Explanations

    Microsoft-related resources/jargon

    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
    DN
    -0.63
     DN
    -0.61
    tagHelperRunner
    -0.60
    nonatomic
    -0.57
     autorytatywna
    -0.57
    Erreferentziak
    -0.57
    useNewUrlParser
    -0.54
     насељу
    -0.54
     shock
    -0.51
    Manbalar
    -0.51
    POSITIVE LOGITS
    ed
    0.65
     ordonn
    0.64
    s
    0.59
    MARKS
    0.58
     reklama
    0.55
    awtextra
    0.55
    Js
    0.52
    cheduling
    0.52
    InjectAttribute
    0.50
     مُعرِّف
    0.50
    Activations Density 0.320%

    No Known Activations