© 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. 0-CLT-HP
    7. 40952
    Prev
    Next
    INDEX
    Explanations

    website

    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
     site
    -2.14
     website
    -1.70
    site
    -1.42
    website
    -1.30
     Site
    -1.25
     Website
    -1.23
    Website
    -1.19
    Site
    -1.18
     sito
    -1.18
    网站
    -1.13
    POSITIVE LOGITS
    tvguidetime
    0.83
     Abp
    0.69
    ViewFeatures
    0.69
     EClass
    0.66
    __(/*!
    0.66
     manqué
    0.65
    ChildScrollView
    0.64
     invokingState
    0.64
    Jegyzetek
    0.64
    providedIn
    0.64
    Activations Density 0.093%

    No Known Activations