© 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. 212
    Prev
    Next
    INDEX
    Explanations

    sequences of numeric tokens and symbols typically associated with complex codes or data patterns

    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
     itſelf
    -1.08
     doubtnut
    -1.00
     Савезне
    -0.98
     Paglinawan
    -0.94
     themſelves
    -0.89
     myſelf
    -0.85
     Anſ
    -0.83
    تقاوى
    -0.83
     Jefus
    -0.82
     Monfieur
    -0.80
    POSITIVE LOGITS
    .
    0.87
    ↵
    0.84
    </strong>
    0.75
    ↵↵
    0.74
    )}}
    0.74
    }$}
    0.70
    ).
    0.67
    </h2>
    0.66
    DoubleQuotes
    0.65
     الرخصة
    0.65
    Activations Density 34.088%

    No Known Activations