© 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. 0-CLT-HP
    7. 92281
    Prev
    Next
    INDEX
    Explanations

    spaces

    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
     places
    -0.88
     spaces
    -0.84
    олові
    -0.65
    places
    -0.64
    spaces
    -0.62
     Efq
    -0.60
     NDEBUG
    -0.59
     locations
    -0.57
    Places
    -0.57
    ItemLayout
    -0.56
    POSITIVE LOGITS
    +#+#
    0.83
     فريبيس
    0.63
    ServiceModel
    0.54
    
    0.53
    ModelSerializer
    0.52
     onOptions
    0.50
    heets
    0.49
     consecu
    0.49
    قایناق‌لار
    0.49
    itele
    0.48
    Activations Density 1.456%

    No Known Activations