Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11208
    Prev
    Next
    INDEX
    Explanations

    nak

    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
    nak
    -1.38
    nek
    -1.06
    NAK
    -0.72
     Edna
    -0.68
    unak
    -0.58
     nak
    -0.57
    PyExc
    -0.50
    s
    -0.50
    nack
    -0.50
    Portály
    -0.48
    POSITIVE LOGITS
    MethodManager
    0.64
     animés
    0.61
    grimas
    0.59
     endfor
    0.58
    جمعیت
    0.57
     AppBundle
    0.57
    RectangleBorder
    0.57
    ñora
    0.57
    Bedroom
    0.56
     vectorielles
    0.56
    Activations Density 0.010%

    No Known Activations