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. 11304
    Prev
    Next
    INDEX
    Explanations

    Disney

    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
    DockStyle
    -0.80
    AccessorTable
    -0.77
    AndEndTag
    -0.68
    numerusform
    -0.68
    ValueStyle
    -0.66
    k
    -0.64
    MessageTagHelper
    -0.61
     dbName
    -0.58
    Compartir
    -0.57
     Abbiamo
    -0.57
    POSITIVE LOGITS
    PostMapping
    0.53
    tagHelper
    0.51
    casing
    0.46
    tableFuture
    0.45
    oltà
    0.45
    ếng
    0.43
     disponibilités
    0.43
    elfth
    0.43
    🏼
    0.42
    poste
    0.42
    Activations Density 0.021%

    No Known Activations