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. 22-CLT-HP
    4. 74555
    Prev
    Next
    INDEX
    Explanations

    the

    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
     utafitiHapana
    -0.82
    DockStyle
    -0.59
     rails
    -0.56
    日閲覧
    -0.53
     railroad
    -0.51
    rails
    -0.51
    Clik
    -0.50
    Sucesor
    -0.49
    antMatchers
    -0.49
     labour
    -0.48
    POSITIVE LOGITS
    ViewImports
    0.66
     TextAppearance
    0.63
    Vidite
    0.59
    complexContent
    0.58
     <=",
    0.56
     Waray
    0.50
    ộng
    0.50
    IntoConstraints
    0.49
     SEDS
    0.49
     föruts
    0.49
    Activations Density 0.163%

    No Known Activations