© 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. 4344
    Prev
    Next
    INDEX
    Explanations

    code snippets or segments related to software interfaces and programming constructs

    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
    otimes
    -0.62
    AVING
    -0.53
    DJANGO
    -0.53
    ⊗
    -0.52
    nage
    -0.51
     "
    -0.50
     di
    -0.48
    зов
    -0.48
     “
    -0.48
    ClientSize
    -0.48
    POSITIVE LOGITS
     nakalista
    0.84
    الإنجليزية
    0.72
     otomatig
    0.71
    脚注の使い方
    0.71
    saraba
    0.70
     onCancelled
    0.69
    </tfoot>
    0.69
     StatefulWidget
    0.65
     Khrushchev
    0.61
     Rajah
    0.61
    Activations Density 0.075%

    No Known Activations