© 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. 3265
    Prev
    Next
    INDEX
    Explanations

    series

    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
    thâu
    -0.60
    SharedCtor
    -0.59
    脚注の使い方
    -0.58
    TintMode
    -0.57
    featureID
    -0.57
    يكب
    -0.55
    RenderAtEndOf
    -0.54
     Wikispecies
    -0.52
    Diwedd
    -0.52
    didSet
    -0.50
    POSITIVE LOGITS
     of
    0.69
    es
    0.51
    '][]
    0.49
     CreateTagHelper
    0.48
    abestanden
    0.47
     Continues
    0.47
     chaining
    0.47
    ětí
    0.45
     topping
    0.45
     Beste
    0.45
    Activations Density 0.008%

    No Known Activations