© 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. 0-CLT-HP
    7. 97271
    Prev
    Next
    INDEX
    Explanations

    strong emotion

    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
    AsUp
    -0.60
    vov
    -0.56
    httphttps
    -0.56
     baffling
    -0.52
     dalamnya
    -0.51
     vast
    -0.51
    uxxxx
    -0.51
    utnik
    -0.50
    statechange
    -0.49
     NSCoder
    -0.48
    POSITIVE LOGITS
    weil
    0.74
    ly
    0.73
    ness
    0.73
    ably
    0.70
     Diſ
    0.69
    ed
    0.68
    aires
    0.68
    withstanding
    0.66
    able
    0.65
     Theſe
    0.65
    Activations Density 0.174%

    No Known Activations