© 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. 4-CLT-HP
    7. 1129
    Prev
    Next
    INDEX
    Explanations

    news/independent sources

    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
     باسم
    -0.47
    kháu
    -0.44
    MigrationBuilder
    -0.41
    IUrlHelper
    -0.40
     Pesca
    -0.40
     Paglinawan
    -0.40
     lyd
    -0.40
     MenuView
    -0.40
    setupUi
    -0.39
     wohin
    -0.39
    POSITIVE LOGITS
    Datuak
    0.86
     Independent
    0.77
    ſelf
    0.70
    ScopeManager
    0.70
     Independ
    0.69
    Independent
    0.69
    Enllaces
    0.66
     independent
    0.65
     independ
    0.60
    independent
    0.60
    Activations Density 0.025%

    No Known Activations