Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11071
    Prev
    Next
    INDEX
    Explanations

    years

    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
    RenderAtEndOf
    -0.93
     years
    -0.57
    TypedDataSet
    -0.56
     Years
    -0.54
    %}
    -0.53
    CopyWith
    -0.53
    脚注の使い方
    -0.53
    )}}{
    -0.52
    évaluateur
    -0.52
    setVerticalGroup
    -0.52
    POSITIVE LOGITS
    pair
    0.57
     éprou
    0.54
     igång
    0.53
     présence
    0.52
    itní
    0.52
    long
    0.51
    main
    0.51
     chré
    0.51
     noires
    0.50
    ERÍA
    0.49
    Activations Density 0.003%

    No Known Activations