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. 74519
    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
    StructEnd
    -0.75
    tamol
    -0.62
    VersionUID
    -0.58
     oprot
    -0.56
    SourceChecksum
    -0.53
     Normdatei
    -0.52
    downe
    -0.49
     اختلاف
    -0.49
    TextWatcher
    -0.47
    uertos
    -0.47
    POSITIVE LOGITS
    Tembelea
    0.63
    WithIOException
    0.59
    Referències
    0.55
    webElementXpaths
    0.53
    Hozzáférés
    0.52
     Signalez
    0.50
     natale
    0.49
    quite
    0.47
     Præ
    0.45
    Diwedd
    0.45
    Activations Density 0.009%

    No Known Activations