© 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. 1-CLT-HP
    7. 863
    Prev
    Next
    INDEX
    Explanations

    cases, size

    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
     “
    -0.50
     
    -0.50
     "
    -0.47
     G
    -0.44
     main
    -0.43
     ‘
    -0.43
     F
    -0.43
     W
    -0.42
    ard
    -0.41
     new
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    1.23
    StructEnd
    1.05
    WebVitals
    1.00
    mergeFrom
    0.98
    EndContext
    0.98
     تضيفلها
    0.97
    AddTagHelper
    0.95
     ExecuteAsync
    0.94
     NSCoder
    0.93
     Audiodateien
    0.93
    Activations Density 0.094%

    No Known Activations