© 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. 96541
    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
    cisme
    -0.52
     Xunit
    -0.50
    wpdb
    -0.49
    orianCalendar
    -0.48
    ="@+
    -0.48
     gyhoeddwyd
    -0.46
     vuitton
    -0.46
     yere
    -0.46
    enschappelijke
    -0.46
     charged
    -0.46
    POSITIVE LOGITS
    edicated
    0.59
    NOPQRST
    0.59
    Bata
    0.53
    AndEndTag
    0.53
     FetchType
    0.52
    eniendo
    0.52
     InputDecoration
    0.50
    jata
    0.49
    mybatisplus
    0.48
    πον
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.