© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1257
    Prev
    Next
    INDEX
    Explanations

    book excerpts

    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
     propOrder
    -0.44
     JFrame
    -0.43
     fragrances
    -0.43
    componentWill
    -0.41
     comparte
    -0.40
     tend
    -0.40
    </caption>
    -0.39
     woj
    -0.39
     feathers
    -0.39
     enzymes
    -0.39
    POSITIVE LOGITS
    клопе
    0.81
    Personendaten
    0.77
    AddHtmlAttribute
    0.75
    iastes
    0.74
    FormTagHelper
    0.73
    styleType
    0.72
    躇
    0.72
    numerusform
    0.71
    GraphicsUnit
    0.69
    RectangleBorder
    0.67
    Activations Density 0.095%

    No Known Activations