© 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. 1-CLT-HP
    4. 12056
    Prev
    Next
    INDEX
    Explanations

    begin/start

    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
     متعلقه
    -0.57
     noDo
    -0.56
     EconPapers
    -0.54
    Personensuche
    -0.45
    *~*~
    -0.45
    Vidite
    -0.44
     }}"></
    -0.43
     gradova
    -0.43
     autorytatywna
    -0.42
    OOTDTY
    -0.41
    POSITIVE LOGITS
     execution
    0.67
    Execution
    0.62
    readystatechange
    0.61
     yyr
    0.57
     fopen
    0.57
    ValueStyle
    0.57
    execution
    0.56
     Execution
    0.56
    XCT
    0.56
    IContainer
    0.54
    Activations Density 0.041%

    No Known Activations