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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1290
    Prev
    Next
    INDEX
    Explanations

    evidence

    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
     ویکی‌پدیا
    -0.76
    PreferredItem
    -0.75
    EndGlobalSection
    -0.71
     viewDidLoad
    -0.68
     createState
    -0.65
    Билгалдахарш
    -0.63
    ViewFeatures
    -0.63
    లాలు
    -0.63
     يتيمه
    -0.60
    featureID
    -0.60
    POSITIVE LOGITS
     now
    0.72
    now
    0.57
     showing
    0.52
     maintenant
    0.52
     shows
    0.48
    الإنجليزية
    0.48
     ormai
    0.48
     artık
    0.48
     mittlerweile
    0.46
     montre
    0.46
    Activations Density 0.006%

    No Known Activations