© 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. 20-CLT-HP
    7. 75442
    Prev
    Next
    INDEX
    Explanations

    code/technical writing

    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
    smithy
    -0.59
    seed
    -0.52
    こそ
    -0.47
    memoized
    -0.47
    ดับ
    -0.46
    wool
    -0.46
    nance
    -0.45
     Mop
    -0.45
    țiuni
    -0.44
     سرخ
    -0.44
    POSITIVE LOGITS
    MethodManager
    0.65
    MessageTagHelper
    0.59
     externi
    0.59
    strconv
    0.59
    ьаж
    0.55
     aDecoder
    0.55
     препратки
    0.55
    UserScript
    0.54
    RectangleBorder
    0.53
    ViewImports
    0.53
    Activations Density 0.000%

    No Known Activations