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. 20-CLT-HP
    4. 74029
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    хьтан
    -0.87
    GEBURTSDATUM
    -0.80
     contextLoads
    -0.80
     pinulongan
    -0.73
    Autoritní
    -0.69
    SafeMath
    -0.69
     intptr
    -0.69
    esgue
    -0.68
     ModelExpression
    -0.68
    Hentet
    -0.67
    POSITIVE LOGITS
     épa
    0.49
     defectos
    0.45
    كلة
    0.41
     bety
    0.41
    industria
    0.40
     físicos
    0.40
    ત્ર
    0.40
    sev
    0.39
     géneros
    0.39
    OCC
    0.38
    Activations Density 0.013%

    No Known Activations