© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2885
    Prev
    Next
    INDEX
    Explanations

    de

    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
    جستارهای
    -0.54
    that
    -0.51
    Lato
    -0.48
    That
    -0.47
    setupUi
    -0.47
     complètes
    -0.46
    and
    -0.46
    unsqueeze
    -0.46
     woods
    -0.45
    ulitan
    -0.45
    POSITIVE LOGITS
     CreateTagHelper
    0.79
    protoimpl
    0.76
    endphp
    0.73
    WebServlet
    0.67
    portál
    0.65
    ScopeManager
    0.63
     مشين
    0.63
     للاسماء
    0.59
    ArgsConstructor
    0.59
    argout
    0.58
    Activations Density 0.000%

    No Known Activations