© 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. 97896
    Prev
    Next
    INDEX
    Explanations

    research studies

    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
    gione
    -0.48
    ıdır
    -0.43
     الحره
    -0.42
    TestingModule
    -0.39
    fib
    -0.38
    closePath
    -0.36
    oł
    -0.35
    Into
    -0.34
     alpina
    -0.34
     lập
    -0.33
    POSITIVE LOGITS
    makeConstraints
    0.67
    ArrowToggle
    0.64
    astéroïdes
    0.63
    AddHtmlAttribute
    0.62
     otomatig
    0.62
     Paglinawan
    0.60
    contentLoaded
    0.59
     Tourists
    0.57
    oluene
    0.57
    mybatisplus
    0.57
    Activations Density 0.006%

    No Known Activations