© 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. 40559
    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
    tonode
    -0.57
     Walkover
    -0.56
    ]]
    -0.49
    mtp
    -0.48
     Lég
    -0.44
     Tramp
    -0.44
    ernoo
    -0.44
    : 
    -0.43
     Prés
    -0.43
     rarer
    -0.43
    POSITIVE LOGITS
     CURIAM
    0.79
    出版年
    0.66
    NamedQueries
    0.63
    archiviato
    0.59
    lillah
    0.59
    قایناق‌لار
    0.59
    FormTagHelper
    0.58
    Tembelea
    0.58
     PackageManager
    0.56
    ReusableCell
    0.52
    Activations Density 1.850%

    No Known Activations