© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94507
    Prev
    Next
    INDEX
    Explanations

    system code

    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
     CreateTagHelper
    -0.90
    tagHelperRunner
    -0.85
     GenerationType
    -0.81
     pinulongan
    -0.75
    ViewImports
    -0.73
     AspNetCore
    -0.69
    ]){
    -0.67
     GetEnumerator
    -0.64
     تضيفلها
    -0.64
     متعلقه
    -0.64
    POSITIVE LOGITS
    contentLoaded
    0.54
    Respectfully
    0.47
     piety
    0.42
     Carthag
    0.42
     backstage
    0.42
    Mutagenicity
    0.41
     boughs
    0.41
     character
    0.41
     consul
    0.41
     troop
    0.41
    Activations Density 0.003%

    No Known Activations