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. 11232
    Prev
    Next
    INDEX
    Explanations

    legal or medical 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
    DotNetBar
    -0.63
    stdafx
    -0.60
    ThroughAttribute
    -0.55
    TestingModule
    -0.53
    NSIndexPath
    -0.53
    CloseOperation
    -0.50
    vänt
    -0.49
     bodyParser
    -0.49
    LabelTagHelper
    -0.48
    ]")]
    -0.48
    POSITIVE LOGITS
     Roskov
    0.65
    geslacht
    0.60
    ultat
    0.60
    DeleteBehavior
    0.59
    
    0.57
    ulity
    0.55
     Andalu
    0.54
    onoi
    0.52
    appliquer
    0.52
     overtime
    0.52
    Activations Density 0.219%

    No Known Activations