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. 22-CLT-HP
    4. 74381
    Prev
    Next
    INDEX
    Explanations

    business and legal contexts

    np_max-act-logits · 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
    SequentialGroup
    -0.82
    verwijspagina
    -0.79
     resourceCulture
    -0.74
     AppColors
    -0.73
    MessageTagHelper
    -0.73
    FieldBuilder
    -0.72
     فريبيس
    -0.71
    ViewFeatures
    -0.71
     DBNull
    -0.69
     betweenstory
    -0.68
    POSITIVE LOGITS
    CodeAttribute
    0.43
    IntoConstraints
    0.42
    ⁡
    0.40
    qing
    0.40
    dele
    0.38
    ্
    0.36
    ULTS
    0.35
     détails
    0.35
    <0xBD>
    0.35
     par
    0.35
    Activations Density 0.023%

    No Known Activations