© 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. 1-CLT-HP
    7. 12955
    Prev
    Next
    INDEX
    Explanations

    she

    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
    manjaro
    -0.64
     aastal
    -0.46
     sebaliknya
    -0.46
     représenter
    -0.44
    ptonshire
    -0.44
     carottes
    -0.43
     segítség
    -0.41
     rehearing
    -0.40
     kéo
    -0.40
    DAOImpl
    -0.39
    POSITIVE LOGITS
     تضيفلها
    0.74
     Roskov
    0.72
     pinulongan
    0.72
    EndGlobalSection
    0.68
    évaluateur
    0.65
    SerializedSize
    0.64
    例文帳に追加
    0.64
     sumpay
    0.64
    TagHelpers
    0.64
    DIPSETTING
    0.64
    Activations Density 0.152%

    No Known Activations