© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4277
    Prev
    Next
    INDEX
    Explanations

    first, second

    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
     eventdata
    -0.57
    WriteTagHelper
    -0.56
    Cyfarwyddwr
    -0.52
     StatelessWidget
    -0.50
    /#{
    -0.49
    ："
    -0.49
     StatefulWidget
    -0.48
    ")){
    -0.48
    /'+
    -0.47
    “...
    -0.47
    POSITIVE LOGITS
     raiſ
    0.59
     examiner
    0.59
    itarianism
    0.58
    helves
    0.58
     demurrer
    0.57
     uſed
    0.57
    holder
    0.57
     تضيفلها
    0.57
     purpoſe
    0.57
     obſ
    0.54
    Activations Density 0.003%

    No Known Activations