© 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. 38458
    Prev
    Next
    INDEX
    Explanations

    Comparisons and duration

    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
     alike
    -1.16
     span
    -0.85
     ControllerBase
    -0.80
     spans
    -0.77
    PhD
    -0.75
    ide
    -0.65
    irus
    -0.64
    endpush
    -0.64
     cruises
    -0.63
     SPAN
    -0.63
    POSITIVE LOGITS
    expandindo
    0.56
    resizingMask
    0.54
    AddTagHelper
    0.51
     kaarangay
    0.50
    الحياه
    0.50
     للمعارف
    0.47
    LookAnd
    0.47
     '\\;'
    0.47
     numberOfRows
    0.46
     gyhoeddwyd
    0.46
    Activations Density 0.472%

    No Known Activations