© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 93999
    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
     الحره
    -0.73
     AssemblyTitle
    -0.70
    SpringBootTest
    -0.62
     autorytatywna
    -0.61
    IBOutlet
    -0.57
     تضيفلها
    -0.56
    SceneManagement
    -0.55
     للاسماء
    -0.54
    routeProvider
    -0.52
    Архівовано
    -0.51
    POSITIVE LOGITS
    PMailer
    0.60
    PullParser
    0.53
     newBuilder
    0.51
    윗
    0.50
    LookAnd
    0.49
    wala
    0.48
    Unmarshaller
    0.47
    oula
    0.47
    век
    0.46
    ATLAS
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.