© 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. 641
    Prev
    Next
    INDEX
    Explanations

    references to specific coded labels or identifiers, likely related to figures, tables, or labeled data

    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
     D
    -0.71
     P
    -0.70
    ENESS
    -0.65
     T
    -0.63
     K
    -0.60
     szolg
    -0.59
     C
    -0.57
     O
    -0.57
     M
    -0.56
     G
    -0.55
    POSITIVE LOGITS
     Anſ
    0.93
     itſelf
    0.91
     houſe
    0.89
     Houſe
    0.88
     myſelf
    0.86
     Reſ
    0.82
     ſever
    0.81
    ſelf
    0.80
     fevere
    0.80
     Monfieur
    0.79
    Activations Density 0.819%

    No Known Activations