© 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. 3496
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    Архівовано
    -0.68
    enumi
    -0.58
    ضات
    -0.56
     disponibilités
    -0.55
    URE
    -0.53
    rizona
    -0.52
    justed
    -0.51
    cona
    -0.51
    setzen
    -0.51
    UDI
    -0.51
    POSITIVE LOGITS
     Audiodateien
    0.59
    LookAnd
    0.59
    Personensuche
    0.57
    ANTLR
    0.56
    AnchorTagHelper
    0.52
    InjectAttribute
    0.52
    SourceChecksum
    0.50
    ypep
    0.48
    Tikang
    0.48
     endwhile
    0.47
    Activations Density 0.002%

    No Known Activations