© 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. 10415
    Prev
    Next
    INDEX
    Explanations

    the structure and formatting of references or citations in scientific writing

    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
    Negative Logits
     مشين
    -0.57
    brink
    -0.54
    aarrggbb
    -0.53
    eaways
    -0.52
     transfieras
    -0.51
    cherichia
    -0.51
    rumah
    -0.50
    LogUtils
    -0.49
    casio
    -0.48
    ectado
    -0.48
    POSITIVE LOGITS
     ddelweddau
    0.75
    Viitteet
    0.66
     estimés
    0.63
    ConstraintMaker
    0.63
     Roskov
    0.61
     Paglinawan
    0.58
    Tikang
    0.57
    homonymie
    0.56
    Cyfarwyddwr
    0.54
    fficients
    0.54
    Activations Density 0.018%

    No Known Activations