© 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. 5-CLT-HP
    7. 96271
    Prev
    Next
    INDEX
    Explanations

    Metal

    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
    StructEnd
    -0.56
    Démographie
    -0.48
    例文帳に追加
    -0.48
     ***!
    -0.44
    sweise
    -0.43
    <eos>
    -0.43
    :][
    -0.42
    riturismo
    -0.42
     <>",
    -0.41
     مشين
    -0.41
    POSITIVE LOGITS
     كومونز
    0.51
    󠁢
    0.50
    WriteTagHelper
    0.48
     Jefus
    0.47
     szabály
    0.47
     récents
    0.47
     termica
    0.47
    AddTagHelper
    0.46
     grève
    0.46
    ofsky
    0.45
    Activations Density 0.005%

    No Known Activations