© 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. 5-CLT-HP
    7. 2289
    Prev
    Next
    INDEX
    Explanations

    to

    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
     viewDidLoad
    -0.54
    saraba
    -0.52
     InputDecoration
    -0.50
    LookAndFeel
    -0.48
    gameserver
    -0.47
    Erstellt
    -0.44
     ComVisible
    -0.44
    kháu
    -0.43
     mattered
    -0.43
    adaptiveStyles
    -0.43
    POSITIVE LOGITS
     custom
    0.75
    انيف
    0.72
    expandindo
    0.69
    matchCondition
    0.67
     instructions
    0.67
     promise
    0.66
    "}")
    0.65
    */)
    0.64
     rules
    0.62
     plan
    0.61
    Activations Density 0.002%

    No Known Activations