© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 9615
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or symbols, particularly relating to inequalities and limits

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    Бахар
    -0.69
    Искәрмәләр
    -0.67
     Orrell
    -0.67
    prnewswire
    -0.64
    RectangleBorder
    -0.62
    httphttps
    -0.62
     Exacts
    -0.61
    doria
    -0.61
    abetes
    -0.61
    liferation
    -0.60
    POSITIVE LOGITS
     resourceCulture
    0.55
    tahankan
    0.52
     estekak
    0.52
     cài
    0.48
     nemlig
    0.46
    getItemId
    0.45
     vàng
    0.44
     jotka
    0.44
     noDo
    0.42
    держание
    0.42
    Activations Density 0.091%

    No Known Activations