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. 0-CLT-HP
    4. 40798
    Prev
    Next
    INDEX
    Explanations

    AAA

    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
    ds
    -0.86
    s
    -0.73
    cy
    -0.69
    ly
    -0.63
    due
    -0.63
    AA
    -0.62
    Cy
    -0.59
    -
    -0.54
    l
    -0.52
     cy
    -0.51
    POSITIVE LOGITS
    AddTagHelper
    1.31
    RenderAtEndOf
    1.20
     CreateTagHelper
    1.09
     تضيفلها
    1.09
     itſelf
    1.05
     дописавши
    1.05
     actionMode
    1.05
     الرياضيه
    1.04
    LookAnd
    1.02
    FormTagHelper
    1.02
    Activations Density 1.862%

    No Known Activations