© 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. 24990
    Prev
    Next
    INDEX
    Explanations

    references to data management and retrieval

    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
    MemoryWarning
    -0.77
     المعيارى
    -0.69
    kiat
    -0.57
    LookAnd
    -0.56
    Twig
    -0.53
    Itoa
    -0.52
    diel
    -0.49
    featureID
    -0.48
    WriteLiteral
    -0.47
     pot
    -0.47
    POSITIVE LOGITS
     pleaſure
    0.69
     ejus
    0.63
    خواندن
    0.61
    raszamy
    0.61
    cupertino
    0.59
     whoſe
    0.58
    hasNext
    0.56
     abbraccio
    0.56
    perrt
    0.55
     poffe
    0.54
    Activations Density 0.074%

    No Known Activations