© 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. 2-RES-MATRYOSHKA-DC
    7. 6406
    Prev
    Next
    INDEX
    Explanations

    expressions of welcoming or invitation

    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
     Trä
    -0.70
    argout
    -0.65
     AssemblyTitle
    -0.64
    fortawesome
    -0.63
    imgur
    -0.63
    skjaer
    -0.63
     ArrayAdapter
    -0.62
    enumi
    -0.62
    opsida
    -0.62
    HtmlAttribute
    -0.60
    POSITIVE LOGITS
     welcome
    3.86
     Welcome
    3.34
    welcome
    3.25
     WELCOME
    3.16
    Welcome
    3.06
     welcomed
    3.00
    WELCOME
    2.83
     welcomes
    2.73
     welcoming
    2.58
     bienvenida
    2.58
    Activations Density 0.008%

    No Known Activations