© 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. 90510
    Prev
    Next
    INDEX
    Explanations

    programming dummy data

    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
     spells
    -0.67
     EconPapers
    -0.65
     weighted
    -0.64
     autorytatywna
    -0.64
    存于互联网档案馆
    -0.63
    躇
    -0.62
     colheres
    -0.60
    WebElementEntity
    -0.59
    weighted
    -0.58
     spikes
    -0.56
    POSITIVE LOGITS
     recognition
    0.48
    CodedInputStream
    0.48
    RunAsync
    0.47
    recognition
    0.47
     Benson
    0.46
    Unmarshaller
    0.46
    OrEqualTo
    0.45
    irov
    0.45
     Recognition
    0.44
    ScopeManager
    0.44
    Activations Density 0.994%

    No Known Activations