© 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. 1-CLT-HP
    7. 10865
    Prev
    Next
    INDEX
    Explanations

    ish/ishing/olytic

    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
     africains
    -0.55
     épis
    -0.51
    ish
    -0.49
    sters
    -0.49
    lán
    -0.48
    cheri
    -0.47
    kozó
    -0.47
    shire
    -0.47
    Thunk
    -0.46
    gers
    -0.46
    POSITIVE LOGITS
     صوتيه
    0.69
    EndGlobalSection
    0.66
    homonymie
    0.58
    StandardCharsets
    0.57
    OpenHelper
    0.56
     DRY
    0.56
     BeautifulSoup
    0.56
    ConstraintMaker
    0.56
     Waray
    0.56
    новниш
    0.55
    Activations Density 0.043%

    No Known Activations