© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1014
    Prev
    Next
    INDEX
    Explanations

    mixed English and Russian code snippets

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     approu
    -0.82
     téléph
    -0.80
     présidenti
    -0.79
     exécut
    -0.78
     néglig
    -0.77
     recev
    -0.76
     financières
    -0.76
     аккура
    -0.74
     amélior
    -0.74
     citoy
    -0.73
    POSITIVE LOGITS
     Yandex
    0.71
     незавершена
    0.66
    CppMethod
    0.66
    المناصب
    0.62
    Билгалдахарш
    0.61
    ьаж
    0.59
     autorytatywna
    0.57
    RenderAtEndOf
    0.57
     Taktlose
    0.56
    GEBURTSDATUM
    0.56
    Activations Density 0.128%

    No Known Activations