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. 74316
    Prev
    Next
    INDEX
    Explanations

    bri

    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
    findpost
    -0.60
    AndEndTag
    -0.57
     ModelExpression
    -0.56
    protoc
    -0.55
    ∎
    -0.54
     minds
    -0.53
    trice
    -0.52
    PreferredItem
    -0.52
     Xer
    -0.52
     machine
    -0.52
    POSITIVE LOGITS
    l
    0.57
     الاطلاع
    0.52
    #+#
    0.49
    da
    0.46
    do
    0.46
    UserScript
    0.45
     jScrollPane
    0.45
    dae
    0.44
    des
    0.43
    #
    0.42
    Activations Density 0.043%

    No Known Activations