© 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. 31286
    Prev
    Next
    INDEX
    Explanations

    references to datasets

    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
     InputDecoration
    -0.86
     TCC
    -0.84
     Lisp
    -0.80
     Cantor
    -0.75
     Herrick
    -0.74
     valentino
    -0.73
    MethodManager
    -0.72
     Calcutta
    -0.72
    contentLoaded
    -0.71
     oorlog
    -0.71
    POSITIVE LOGITS
    datasets
    1.24
     datasets
    1.23
     Dataset
    1.22
     dataset
    1.17
    dataset
    1.14
    Dataset
    1.13
    Datasets
    1.13
     Datasets
    1.12
    TypedDataSet
    1.00
    DATASET
    0.93
    Activations Density 0.009%

    No Known Activations