© 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. 12-RES-MATRYOSHKA-DC
    7. 22205
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting elements in legal documents

    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
    kháu
    -0.80
     Wikimedijinoj
    -0.75
     يتيمه
    -0.74
     referenties
    -0.72
     مرئيه
    -0.72
     nakalista
    -0.69
     autorytatywna
    -0.66
     Würde
    -0.66
     Chwiliwch
    -0.66
    Tembelea
    -0.66
    POSITIVE LOGITS
    лье
    0.50
     UnityEngine
    0.46
    rouvez
    0.43
     sh
    0.43
    avyzd
    0.42
     SafeMath
    0.42
    штей
    0.42
     skjø
    0.42
     noqa
    0.41
    enerys
    0.41
    Activations Density 0.006%

    No Known Activations