© 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. 9343
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of mechanical components and their configurations

    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
     chofe
    -0.65
     poffe
    -0.63
     reafon
    -0.63
     deſt
    -0.63
    SharedCtor
    -0.61
     fhew
    -0.59
    gonic
    -0.59
     Monfieur
    -0.57
     uſed
    -0.56
     Gallimard
    -0.55
    POSITIVE LOGITS
     pattern
    0.63
     '\\;'
    0.62
     detail
    0.60
     patterns
    0.60
    elemField
    0.57
    érien
    0.57
    enumerate
    0.56
    detail
    0.54
     OMITBAD
    0.54
     Patterns
    0.53
    Activations Density 0.132%

    No Known Activations