© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75540
    Prev
    Next
    INDEX
    Explanations

    Antif

    np_max-act-logits · 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
    BeginContext
    -0.73
     frame
    -0.64
     تضيفلها
    -0.63
    frame
    -0.61
    setVerticalGroup
    -0.60
     Energies
    -0.57
     Frame
    -0.56
    EndGlobalSection
    -0.56
     Valer
    -0.56
     frames
    -0.55
    POSITIVE LOGITS
    الدراسه
    0.51
     colorés
    0.50
     errori
    0.48
     insectes
    0.46
     leçons
    0.46
     journaux
    0.45
     réfugiés
    0.43
    asio
    0.42
    HtmlAttribute
    0.42
    SequentialGroup
    0.42
    Activations Density 0.001%

    No Known Activations