© 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. 564
    Prev
    Next
    INDEX
    Explanations

    mentions of specific named locations or designs related to infrastructure or engineering components

    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
     PNP
    -0.97
    UpdateCommand
    -0.94
     umbi
    -0.91
     itſelf
    -0.91
    aarrggbb
    -0.90
     Hutton
    -0.90
     Catto
    -0.86
    fraid
    -0.86
    клопе
    -0.84
     NTB
    -0.84
    POSITIVE LOGITS
     Kish
    0.85
     Landis
    0.85
     Kraus
    0.84
    brace
    0.82
     Jacobsen
    0.81
    ━━━
    0.76
     Nicholson
    0.72
     Harris
    0.72
     balan
    0.72
     Gour
    0.69
    Activations Density 5.615%

    No Known Activations