© 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. 5-CLT-HP
    7. 97849
    Prev
    Next
    INDEX
    Explanations

    adverbs

    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
    Cyfeiriadau
    -0.60
    
    -0.56
    Sucesor
    -0.54
     surla
    -0.52
     Exactos
    -0.50
    はじめに
    -0.50
     AttributeSet
    -0.49
    showing
    -0.48
    脚注の使い方
    -0.46
     ModelExpression
    -0.46
    POSITIVE LOGITS
     houſe
    0.66
     preſent
    0.65
     leaſt
    0.65
     themſelves
    0.64
     himſelf
    0.62
     beſt
    0.61
     Jefus
    0.61
     Majefty
    0.60
     ſmall
    0.60
     purpoſe
    0.59
    Activations Density 0.002%

    No Known Activations