© 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. 21155
    Prev
    Next
    INDEX
    Explanations

    references to different models, designs, or concepts in technology and biology

    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
    maan
    -0.49
     Ac
    -0.49
    </thead>
    -0.47
    Documents
    -0.47
     document
    -0.47
    document
    -0.46
    CSM
    -0.45
    <eos>
    -0.45
     documents
    -0.45
    iones
    -0.44
    POSITIVE LOGITS
    Geplaatst
    0.69
     CURLOPT
    0.69
    曖昧さ回避
    0.66
     InputDecoration
    0.62
     تانيه
    0.62
     الحره
    0.60
     дописавши
    0.59
    Izvori
    0.59
     IDisposable
    0.59
    wpi
    0.58
    Activations Density 0.306%

    No Known Activations