© 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. 6138
    Prev
    Next
    INDEX
    Explanations

    various numerical representations or statistics

    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
    KEE
    -0.54
     Al
    -0.52
    APIView
    -0.51
    ".$
    -0.50
     AL
    -0.50
     vold
    -0.50
     T
    -0.49
    uris
    -0.49
    //$
    -0.48
    //
    -0.48
    POSITIVE LOGITS
     فريبيس
    0.96
     resourceCulture
    0.96
     للاسماء
    0.93
    awtextra
    0.90
     autorytatywna
    0.85
    AndEndTag
    0.85
     صوتيه
    0.83
    ValueStyle
    0.83
    tagHelperRunner
    0.81
     itſelf
    0.80
    Activations Density 0.052%

    No Known Activations