© 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. 4-CLT-HP
    7. 2564
    Prev
    Next
    INDEX
    Explanations

    way

    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
    
    -0.82
    ilh
    -0.68
    참고
    -0.66
     Loomis
    -0.60
    Rujukan
    -0.60
     Sycamore
    -0.59
    enderror
    -0.59
    aitu
    -0.57
    SNA
    -0.57
     invertible
    -0.56
    POSITIVE LOGITS
     into
    1.09
     onto
    0.71
    出版年
    0.69
    into
    0.69
    Into
    0.67
     Into
    0.63
     INTO
    0.59
     to
    0.51
    findpost
    0.49
    neté
    0.48
    Activations Density 0.002%

    No Known Activations