Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12710
    Prev
    Next
    INDEX
    Explanations

    mentary

    np_max-act · 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
    mentary
    -0.59
    ular
    -0.49
    odendron
    -0.48
     dAtA
    -0.45
     Express
    -0.45
    neet
    -0.44
    an
    -0.43
    bitField
    -0.42
    tong
    -0.42
    arja
    -0.41
    POSITIVE LOGITS
     незавершена
    0.77
    RectangleBorder
    0.66
    MLLoader
    0.66
     تضيفلها
    0.65
     ComVisible
    0.64
    stateProvider
    0.63
    ScopeManager
    0.63
    ModelAdmin
    0.63
    Diwedd
    0.62
     مشين
    0.61
    Activations Density 0.019%

    No Known Activations