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. 20-CLT-HP
    4. 74266
    Prev
    Next
    INDEX
    Explanations

    Code/technical language

    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
    WithIOException
    -0.71
     <>",
    -0.54
    simpleType
    -0.54
    audiovisuel
    -0.53
    webElementXpaths
    -0.51
    queur
    -0.50
     Yani
    -0.49
     dépla
    -0.48
    twimg
    -0.48
    richTextPanel
    -0.47
    POSITIVE LOGITS
    AddTagHelper
    0.62
     >=",
    0.56
    MLLoader
    0.52
    TagMode
    0.48
    AttributeSet
    0.45
     виправивши
    0.44
    atelli
    0.44
    Pvt
    0.44
    viewDid
    0.44
    FormTagHelper
    0.43
    Activations Density 0.001%

    No Known Activations