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. 1-CLT-HP
    4. 11142
    Prev
    Next
    INDEX
    Explanations

    science and legal texts

    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
    TRI
    -0.71
    MLLoader
    -0.69
     TRI
    -0.65
    res
    -0.56
    ViewImports
    -0.56
     Keene
    -0.50
    ьаж
    -0.48
    anyeol
    -0.47
    Subview
    -0.47
    mehl
    -0.47
    POSITIVE LOGITS
    setVerticalGroup
    0.72
    IntoConstraints
    0.53
    envoy
    0.50
     apostar
    0.49
    lwjgl
    0.47
     attravers
    0.47
     terk
    0.47
     समीक्षाओं
    0.47
     læng
    0.46
     noDo
    0.46
    Activations Density 0.023%

    No Known Activations