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. 74474
    Prev
    Next
    INDEX
    Explanations

    Cave

    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
    ThroughAttribute
    -0.65
    RegressionTest
    -0.60
    verwijspagina
    -0.60
    withIdentifier
    -0.59
    complexContent
    -0.56
    webElementXpaths
    -0.56
    GEBURTSDATUM
    -0.55
    hésitez
    -0.54
     "..\..\
    -0.53
    $_['
    -0.53
    POSITIVE LOGITS
     finds
    0.52
    issus
    0.51
     Secondary
    0.50
    zied
    0.50
    "];
    
    0.49
     Central
    0.49
     delivers
    0.48
     Older
    0.47
    ']>
    0.46
    OPSIS
    0.46
    Activations Density 0.001%

    No Known Activations