© 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. 96413
    Prev
    Next
    INDEX
    Explanations

    percent

    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
    twimg
    -0.70
     resourceCulture
    -0.64
    তথ্যসূত্র
    -0.59
    lač
    -0.54
    tagHelperRunner
    -0.53
     tended
    -0.53
     CreateTagHelper
    -0.53
    例句
    -0.52
     propOrder
    -0.52
    Termine
    -0.51
    POSITIVE LOGITS
    SPATH
    0.55
    ValueGeneration
    0.54
    出版年
    0.49
    тату
    0.48
     use
    0.48
     AssemblyCompany
    0.47
    webElementGuid
    0.46
    
    0.45
    ած
    0.43
    FontOfSize
    0.43
    Activations Density 0.004%

    No Known Activations