© 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. 94316
    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
    OrNil
    -0.66
    ValueStyle
    -0.62
    PreferredItem
    -0.59
     otomatig
    -0.56
    +#+#
    -0.54
    ToolStripButton
    -0.54
    出版年
    -0.53
     enz
    -0.51
     Incub
    -0.50
    tvguidetime
    -0.50
    POSITIVE LOGITS
    defined
    0.57
    specifically
    0.56
     comprising
    0.56
    i
    0.55
    }{*}{}
    0.55
    ulado
    0.53
    ="#"><
    0.53
    including
    0.53
    particularly
    0.52
    собенно
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.