© 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. 25422
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or codes indicating legal or regulatory references

    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
     propOrder
    -0.90
    tvguidetime
    -0.84
    帖最后由
    -0.81
     otomatig
    -0.76
     autorytatywna
    -0.73
    createClass
    -0.71
     препратки
    -0.71
     AspNetCore
    -0.70
    huit
    -0.70
    헌
    -0.70
    POSITIVE LOGITS
     Spit
    0.61
     Dord
    0.61
     kil
    0.60
     Agung
    0.58
     Unic
    0.57
     Rostock
    0.57
     assoluto
    0.57
    rzost
    0.55
    <i>
    0.55
     Nam
    0.55
    Activations Density 0.080%

    No Known Activations