© 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. 45356
    Prev
    Next
    INDEX
    Explanations

    Tsar

    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
    UIControlState
    -1.00
    AddTagHelper
    -0.76
    Życiorys
    -0.74
     protoimpl
    -0.70
     EconPapers
    -0.69
    RenderAtEndOf
    -0.69
     gql
    -0.67
    脚注の使い方
    -0.66
    abetes
    -0.66
    WebVitals
    -0.64
    POSITIVE LOGITS
     Jefus
    0.91
     Monfieur
    0.86
     houſe
    0.84
     pleaſure
    0.80
     ſche
    0.73
     Reſ
    0.73
     Chriftian
    0.69
     Houſe
    0.69
     Conſ
    0.68
     Efq
    0.68
    Activations Density 1.528%

    No Known Activations