© 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. 5-CLT-HP
    7. 2831
    Prev
    Next
    INDEX
    Explanations

    questions or problems

    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
     StatelessWidget
    -0.71
    extField
    -0.56
    Portály
    -0.56
    ніципалі
    -0.54
     jsPsych
    -0.54
    prefixer
    -0.52
     بيها
    -0.48
    
    -0.48
    ագրություններ
    -0.48
     StatefulWidget
    -0.46
    POSITIVE LOGITS
    bulo
    0.61
    AddTagHelper
    0.59
     preocu
    0.57
     propOrder
    0.56
     of
    0.54
     tolerated
    0.52
     anymore
    0.51
     kompati
    0.50
    ConstraintMaker
    0.49
     kovo
    0.49
    Activations Density 0.001%

    No Known Activations