© 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. 94762
    Prev
    Next
    INDEX
    Explanations

    sparse

    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
     fiss
    -0.52
     nan
    -0.51
    nan
    -0.49
    findpost
    -0.49
    Errorf
    -0.48
    tagext
    -0.47
     Warga
    -0.47
    EventHandler
    -0.46
    AlterField
    -0.46
    ImageField
    -0.46
    POSITIVE LOGITS
     виправивши
    0.62
    RectangleBorder
    0.60
    verwijspagina
    0.59
    scriptId
    0.57
    łaszcza
    0.57
    grà
    0.57
     itſelf
    0.56
     himſelf
    0.56
    addCriterion
    0.55
    脚注の使い方
    0.54
    Activations Density 0.002%

    No Known Activations