© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93613
    Prev
    Next
    INDEX
    Explanations

    system

    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
     system
    -1.98
    system
    -1.92
     SYSTEM
    -1.73
     System
    -1.70
    System
    -1.69
    SYSTEM
    -1.50
     sistema
    -1.48
     système
    -1.48
     systems
    -1.46
    ystem
    -1.42
    POSITIVE LOGITS
    TypedDataSet
    0.62
    ,
    0.60
    typeorm
    0.52
    WriteBarrier
    0.50
     CERN
    0.49
    .
    0.48
    createStatement
    0.48
     LHC
    0.48
     divisors
    0.47
     divisible
    0.47
    Activations Density 0.122%

    No Known Activations