© 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. 0-CLT-HP
    7. 1041
    Prev
    Next
    INDEX
    Explanations

    professional/educational services

    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
    .
    -0.52
    {
    -0.49
     paie
    -0.45
     {
    -0.45
    סק
    -0.44
    g
    -0.44
    S
    -0.44
    v
    -0.44
    G
    -0.44
    GeneratedMessage
    -0.43
    POSITIVE LOGITS
     Wikimedijinoj
    0.93
    )";
    0.92
    %";
    0.89
    ValueStyle
    0.84
    $.
    0.81
    .";
    0.80
    rrggbb
    0.77
     समीक्षाओं
    0.77
    MessageTagHelper
    0.76
     Administrativna
    0.76
    Activations Density 0.054%

    No Known Activations