© 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. 1-CLT-HP
    7. 13301
    Prev
    Next
    INDEX
    Explanations

    some

    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
     للمعارف
    -0.72
     protoimpl
    -0.67
     مرئيه
    -0.65
     تانيه
    -0.64
    AccessorTable
    -0.57
     ffilm
    -0.55
    
    -0.52
    же
    -0.46
    WebServlet
    -0.46
    dhury
    -0.45
    POSITIVE LOGITS
     cases
    0.99
     instances
    0.72
    cases
    0.69
     Cases
    0.67
     ways
    0.65
     manner
    0.64
     contexts
    0.64
     way
    0.63
     circumstances
    0.62
     przypad
    0.62
    Activations Density 0.067%

    No Known Activations