© 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. 17147
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to network structures and interactions

    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
     Efq
    -0.91
     Theſe
    -0.88
     Monfieur
    -0.86
     ſeveral
    -0.86
     itſelf
    -0.85
     myſelf
    -0.84
    ReusableCell
    -0.83
     Beſ
    -0.83
    principalColumn
    -0.81
    ArgsConstructor
    -0.78
    POSITIVE LOGITS
    <eos>
    0.47
     between
    0.44
     skjer
    0.43
     consulta
    0.43
     például
    0.40
     [
    0.40
     $
    0.39
     
    0.38
    chemise
    0.38
    ?
    0.38
    Activations Density 0.092%

    No Known Activations