© 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. 5-CLT-HP
    7. 287
    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
     betweenstory
    -0.90
    VersionUID
    -0.88
     تضيفلها
    -0.82
     resourceCulture
    -0.81
    bootstrapcdn
    -0.81
    DockStyle
    -0.78
    tagHelperRunner
    -0.78
     noDo
    -0.75
     متعلقه
    -0.73
    ViewFeatures
    -0.71
    POSITIVE LOGITS
     Powder
    0.38
     aufgestellt
    0.37
     Bren
    0.36
    λέον
    0.36
     banded
    0.35
     blown
    0.34
    bres
    0.34
     الحدي
    0.34
     pedig
    0.34
     exception
    0.34
    Activations Density 0.000%

    No Known Activations