© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73285
    Prev
    Next
    INDEX
    Explanations

    business, tech, abbreviations

    np_max-act-logits · 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
     CreateTagHelper
    -0.64
     onCancelled
    -0.55
     Buddhists
    -0.54
    katy
    -0.45
     Sosial
    -0.45
     escudo
    -0.44
     Princesa
    -0.43
    mexic
    -0.43
    Viungo
    -0.43
     Technolog
    -0.43
    POSITIVE LOGITS
     ModelExpression
    0.87
     propOrder
    0.63
    apimachinery
    0.63
    }}/>
    0.62
    WriteTagHelper
    0.58
     للاسماء
    0.58
     mand
    0.58
    DeleteBehavior
    0.57
     Pure
    0.56
    contentLoaded
    0.56
    Activations Density 0.000%

    No Known Activations