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. 40887
    Prev
    Next
    INDEX
    Explanations

    scheduling, time, medical

    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
     Hour
    -0.70
    ature
    -0.65
    edy
    -0.56
    cale
    -0.56
    ence
    -0.55
    Hour
    -0.55
    elle
    -0.54
    arily
    -0.54
    mators
    -0.52
    ọa
    -0.52
    POSITIVE LOGITS
    ChildScrollView
    0.72
    kháu
    0.68
    ($__
    0.67
     '\\;'
    0.62
     informée
    0.62
    BeginInit
    0.62
    numerusform
    0.57
     bezeichneter
    0.57
    UVWXYZ
    0.57
    StoryboardSegue
    0.57
    Activations Density 0.869%

    No Known Activations