© 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. 1481
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    dane
    -0.47
     monasterio
    -0.46
    GOTREF
    -0.45
    bootstrapcdn
    -0.45
     påvir
    -0.44
    opan
    -0.44
    army
    -0.43
     palav
    -0.43
    равда
    -0.43
    putInt
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.92
    igshid
    0.69
    RuleContext
    0.69
    InjectAttribute
    0.65
     Memoir
    0.65
     kaarangay
    0.65
     readline
    0.63
    spyOn
    0.60
    IUrlHelper
    0.59
     sache
    0.58
    Activations Density 1.580%

    No Known Activations