© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43927
    Prev
    Next
    INDEX
    Explanations

    code or legal documents

    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
    تقاوى
    -0.68
    migrationBuilder
    -0.63
    KommentareTeilen
    -0.62
     Mocking
    -0.61
    DockStyle
    -0.60
     EdgeInsets
    -0.60
    DoubleQuotes
    -0.60
    Tembelea
    -0.59
     utafitiHapana
    -0.58
     intptr
    -0.57
    POSITIVE LOGITS
    TagMode
    0.63
     căr
    0.56
    minator
    0.55
     Then
    0.53
     then
    0.52
     gevol
    0.52
    Then
    0.51
    olari
    0.50
    efte
    0.50
    then
    0.49
    Activations Density 1.691%

    No Known Activations