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. 74475
    Prev
    Next
    INDEX
    Explanations

    punctuation/code symbols

    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
     المعيارى
    -0.56
    inée
    -0.49
    messageInfo
    -0.49
    Portail
    -0.46
    msgs
    -0.46
     central
    -0.46
    saga
    -0.46
    oneg
    -0.46
    parsedMessage
    -0.46
     oprot
    -0.44
    POSITIVE LOGITS
     Мексичка
    0.60
    ">—
    0.58
    fbox
    0.54
     Pfar
    0.54
    ::_('
    0.53
    InputModule
    0.53
    sizeCache
    0.52
     uintptr
    0.52
    Бахар
    0.52
     Normdatei
    0.49
    Activations Density 0.000%

    No Known Activations