© 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. 0-CLT-HP
    4. 1348
    Prev
    Next
    INDEX
    Explanations

    sharing

    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
     Sharing
    -1.07
     sharing
    -1.05
    sharing
    -1.03
    Sharing
    -1.00
     Shared
    -0.61
     cartaz
    -0.60
     OnTriggerEnter
    -0.59
    setof
    -0.58
     shared
    -0.57
     Diſ
    -0.57
    POSITIVE LOGITS
    <bos>
    0.63
    ABUL
    0.61
    تقاوى
    0.59
     الرياضيه
    0.56
     gyhoeddwyd
    0.56
     himo
    0.55
    Климат
    0.54
     gra
    0.53
     оригіналу
    0.53
    jsxFileName
    0.53
    Activations Density 0.047%

    No Known Activations