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. 74322
    Prev
    Next
    INDEX
    Explanations

    names/titles

    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
     createState
    -0.76
    medriver
    -0.74
    esModule
    -0.68
    tagHelperRunner
    -0.66
     DriverManager
    -0.63
     ModelAndView
    -0.62
    IBarButtonItem
    -0.62
    CppMethod
    -0.61
    Literatuur
    -0.59
     صوتيه
    -0.59
    POSITIVE LOGITS
    Geplaatst
    0.57
    Бахар
    0.43
     Amat
    0.41
     Kuma
    0.41
    Ổ
    0.41
    urf
    0.40
     Crockett
    0.39
     Savo
    0.37
     pot
    0.37
    CÓ
    0.37
    Activations Density 0.003%

    No Known Activations