© 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. 0-RES-MATRYOSHKA-DC
    7. 11587
    Prev
    Next
    INDEX
    Explanations

    sequences of special codes or identifiers, specifically those starting with 'xd' followed by a number

    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
     Houſe
    -0.81
     Reſ
    -0.79
     myſelf
    -0.75
     Monfieur
    -0.74
     Eſ
    -0.73
     purpoſe
    -0.73
     ſever
    -0.71
     Diſ
    -0.70
     Conſ
    -0.69
    ^(@)
    -0.69
    POSITIVE LOGITS
    xd
    2.70
    XD
    1.89
    xD
    1.36
     xd
    1.31
     XD
    1.12
    ChildScrollView
    0.72
    zd
    0.65
    Xd
    0.65
     Hig
    0.60
    الإنجليزية
    0.56
    Activations Density 0.004%

    No Known Activations