© 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. 4-CLT-HP
    7. 3132
    Prev
    Next
    INDEX
    Explanations

    Damascus

    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
     nakalista
    -0.64
    RuleContext
    -0.48
     चीज़ों
    -0.46
     erw
    -0.45
    Meister
    -0.43
    reide
    -0.43
     memes
    -0.42
    meister
    -0.42
    atrième
    -0.42
     resisted
    -0.42
    POSITIVE LOGITS
    DrawerToggle
    0.65
     متعلقه
    0.64
     transfieras
    0.59
    afficheront
    0.58
    dit
    0.57
    تقاوى
    0.56
    
    0.56
     فريبيس
    0.54
     []:
    0.54
    latego
    0.54
    Activations Density 0.002%

    No Known Activations