© 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. 3528
    Prev
    Next
    INDEX
    Explanations

    verb "to be"

    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
     three
    -1.23
    three
    -1.09
     trois
    -1.01
    三个
    -0.97
     três
    -0.96
     तीन
    -0.95
     drei
    -0.93
    Three
    -0.92
     Three
    -0.91
     ketiga
    -0.90
    POSITIVE LOGITS
    AddTagHelper
    0.62
     surla
    0.60
     Fifty
    0.59
    InjectAttribute
    0.57
    __))
    0.56
     AssemblyCulture
    0.56
    enumii
    0.56
    UrlResolution
    0.55
    ksikon
    0.54
    Diweddarwch
    0.54
    Activations Density 0.007%

    No Known Activations