© 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. 1-CLT-HP
    7. 46116
    Prev
    Next
    INDEX
    Explanations

    press

    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
    Билгалдахарш
    -0.77
    AnchorStyles
    -0.73
     мәкал
    -0.71
     autorytatywna
    -0.69
    StoryboardSegue
    -0.66
     Meksiku
    -0.64
    RegressionTest
    -0.63
    WindowConstants
    -0.63
     getItemCount
    -0.62
    MLLoader
    -0.61
    POSITIVE LOGITS
    ınt
    0.49
    unately
    0.46
    enty
    0.44
    ன்ற
    0.43
     hearers
    0.43
     siy
    0.43
    setattr
    0.41
     urbanas
    0.41
    ntz
    0.41
    Translator
    0.40
    Activations Density 0.002%

    No Known Activations