© 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. 5-CLT-HP
    4. 895
    Prev
    Next
    INDEX
    Explanations

    statements/assertions

    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
     me
    -0.50
    webElementXpaths
    -0.48
    Me
    -0.45
     Me
    -0.42
    Force
    -0.41
     plutôt
    -0.41
    ğından
    -0.40
     Force
    -0.38
     avantages
    -0.37
     Wikimedijinoj
    -0.37
    POSITIVE LOGITS
     StatefulWidget
    0.83
    BeginInit
    0.82
    +#+
    0.78
    DllImport
    0.75
     onItemClick
    0.70
     AssemblyProduct
    0.70
    IRQn
    0.69
    ;">
    
    0.68
    DispatchToProps
    0.67
     invokingState
    0.67
    Activations Density 0.010%

    No Known Activations