© 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. 0-CLT-HP
    7. 43495
    Prev
    Next
    INDEX
    Explanations

    Motion, sequences, responsiveness

    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
    ValueStyle
    -1.05
     photolibrary
    -1.01
    XmlAccessorType
    -0.93
     ainfi
    -0.90
    FundMe
    -0.88
     Thine
    -0.88
     Chaldean
    -0.88
     Cæsar
    -0.86
    TagMode
    -0.86
     ་་
    -0.84
    POSITIVE LOGITS
     par
    0.66
     Par
    0.61
     non
    0.61
      
    0.59
     E
    0.59
     In
    0.57
     
    0.57
     in
    0.55
     M
    0.55
     a
    0.54
    Activations Density 0.082%

    No Known Activations