© 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. 0-CLT-HP
    7. 43689
    Prev
    Next
    INDEX
    Explanations

    sophisticated vocabulary

    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
     prisonniers
    -0.68
    estimable
    -0.66
    VIAF
    -0.65
    e
    -0.65
    الحياه
    -0.64
    
    -0.63
     &___
    -0.62
    !*\
    -0.62
     henvisninger
    -0.60
    锈钢
    -0.60
    POSITIVE LOGITS
     pleaſure
    0.70
     ſmall
    0.61
     Houſe
    0.56
     miſ
    0.56
     ſche
    0.55
     houſe
    0.55
     chup
    0.55
     EDR
    0.53
     reaſon
    0.53
     ſtre
    0.53
    Activations Density 0.065%

    No Known Activations