© 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. 1-CLT-HP
    7. 46049
    Prev
    Next
    INDEX
    Explanations

    trainer

    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
    <bos>
    -0.88
    
    -0.51
    war
    -0.44
    gelöst
    -0.44
    šić
    -0.43
     Leinwand
    -0.43
     mechanism
    -0.42
     guidance
    -0.41
    Jereo
    -0.41
    ScopeManager
    -0.41
    POSITIVE LOGITS
     AssemblyProduct
    0.71
    sizeCache
    0.70
    IndentedString
    0.69
    findpost
    0.69
    WebVitals
    0.66
     EconPapers
    0.65
    
    0.63
    Personendaten
    0.63
    tagHelperRunner
    0.62
    adaptiveStyles
    0.61
    Activations Density 0.033%

    No Known Activations