© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13444
    Prev
    Next
    INDEX
    Explanations

    crust or nomination

    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
     crust
    -1.68
     Crust
    -1.55
    crust
    -1.42
    Crust
    -1.25
    aarrggbb
    -0.75
    InstrumentedTest
    -0.65
    WebServlet
    -0.59
    ItemBackground
    -0.58
    IContainer
    -0.56
     createSprite
    -0.56
    POSITIVE LOGITS
    ViewImports
    0.65
    s
    0.64
    acea
    0.58
    ی
    0.57
    al
    0.56
    y
    0.56
    áce
    0.54
     [*]
    0.51
    Personendaten
    0.50
    ing
    0.49
    Activations Density 0.009%

    No Known Activations