© 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. 4461
    Prev
    Next
    INDEX
    Explanations

    XB

    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
     autorytatywna
    -0.77
    ANTLR
    -0.71
    Rüyada
    -0.65
     Walkover
    -0.64
    rungsseite
    -0.64
    таратура
    -0.64
    참고
    -0.63
     հղումներ
    -0.62
    DoubleQuotes
    -0.61
    webElementXpaths
    -0.59
    POSITIVE LOGITS
     gangen
    0.46
    zzly
    0.45
    NUMX
    0.44
    andExpect
    0.43
    omiast
    0.42
     INTERESAR
    0.41
    `.`
    0.39
    ModelBuilder
    0.39
    ก่
    0.39
    ztyn
    0.39
    Activations Density 0.002%

    No Known Activations