© 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. 38950
    Prev
    Next
    INDEX
    Explanations

    start or end

    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
     fumée
    -0.64
     ciasc
    -0.59
     that
    -0.52
     autrement
    -0.52
     the
    -0.51
     rispet
    -0.50
     helyzet
    -0.49
     poussière
    -0.48
     fidélité
    -0.48
     altrimenti
    -0.48
    POSITIVE LOGITS
    AddTagHelper
    1.06
     thing
    0.95
     couple
    0.88
     MainAxisSize
    0.88
     ExecuteAsync
    0.85
    MessageOf
    0.85
     brunt
    0.83
     few
    0.82
     Paglinawan
    0.82
     moment
    0.82
    Activations Density 0.127%

    No Known Activations