© 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. 9938
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical data or 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
     Audiodateien
    -0.95
    WriteTagHelper
    -0.94
     >=",
    -0.91
    BufferException
    -0.89
     فريبيس
    -0.87
     שוליים
    -0.86
    Билгалдахарш
    -0.86
     ویکی‌پدیای
    -0.84
    GEBURTS
    -0.83
     CreateTagHelper
    -0.83
    POSITIVE LOGITS
     last
    0.50
    ,
    0.49
     
    0.48
    .
    0.46
    ?
    0.45
    ;
    0.45
     “
    0.44
    <eos>
    0.41
     at
    0.41
      
    0.40
    Activations Density 0.025%

    No Known Activations