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. 74304
    Prev
    Next
    INDEX
    Explanations

    code, technical text

    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
    #+#
    -0.54
    ctools
    -0.53
    liwości
    -0.48
    AccessorTable
    -0.46
    fony
    -0.45
    DropTable
    -0.44
     تعدى
    -0.44
    NewUrlParser
    -0.43
    lifer
    -0.41
    ग्री
    -0.41
    POSITIVE LOGITS
     تضيفلها
    0.71
    муж
    0.59
    toHaveBeenCalled
    0.54
     يتيمه
    0.53
    Ữ
    0.53
     محفوظة
    0.52
    LogFactory
    0.50
     Bassett
    0.50
    DrawerToggle
    0.49
    Хьажоргаш
    0.49
    Activations Density 0.003%

    No Known Activations