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. 22-CLT-HP
    4. 74271
    Prev
    Next
    INDEX
    Explanations

    programming and technical

    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
     coton
    -0.54
     Immort
    -0.53
     spf
    -0.53
    SPF
    -0.52
     nant
    -0.51
    otonin
    -0.51
     Chaplin
    -0.50
     antimony
    -0.49
     monasteries
    -0.49
     Gallen
    -0.48
    POSITIVE LOGITS
    OGND
    0.72
     Мексичка
    0.66
    تقاوى
    0.58
     K
    0.58
    Geplaatst
    0.57
     formal
    0.54
    formal
    0.53
     autorytatywna
    0.52
    webElementXpaths
    0.52
    :][
    0.52
    Activations Density 0.017%

    No Known Activations