© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 640
    Prev
    Next
    INDEX
    Explanations

    references to server-related concepts or the word "server"

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    льник
    -0.52
     Boko
    -0.52
    Referensi
    -0.52
     xiaomi
    -0.50
     programa
    -0.49
     getan
    -0.49
    ker
    -0.48
     Beecher
    -0.48
     Whittier
    -0.47
     hộ
    -0.47
    POSITIVE LOGITS
     server
    4.34
     Server
    4.03
    server
    3.88
    Server
    3.69
     servers
    3.55
     SERVER
    3.39
     Servers
    3.39
    SERVER
    3.08
     serveur
    3.03
    服务器
    2.80
    Activations Density 0.064%

    No Known Activations