© 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. 20466
    Prev
    Next
    INDEX
    Explanations

    various types of deficiencies or issues, particularly related to the evaluation of performance or experiences

    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
     AssemblyProduct
    -0.71
     насељу
    -0.68
     Bourgoin
    -0.63
     ModelExpression
    -0.60
    уза
    -0.58
    таратура
    -0.57
    htë
    -0.57
    
    -0.56
    +:+
    -0.55
    setVerticalGroup
    -0.54
    POSITIVE LOGITS
    IsContent
    0.68
    SharedDtor
    0.55
     gevolg
    0.52
     root
    0.52
     lack
    0.48
     Infórmanos
    0.48
    nextElement
    0.48
     Prohibition
    0.47
     rencont
    0.47
     contextLoads
    0.47
    Activations Density 0.340%

    No Known Activations