© 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. 9485
    Prev
    Next
    INDEX
    Explanations

    terms related to properties and characteristics of subjects in scientific contexts

    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
     giusti
    -0.78
     extérieurs
    -0.73
    seamnă
    -0.73
    antaranya
    -0.71
     tromper
    -0.68
    SuppressMessage
    -0.68
     armée
    -0.67
    SequentialGroup
    -0.66
     aucun
    -0.65
     réfugi
    -0.65
    POSITIVE LOGITS
     properties
    0.65
    properties
    0.57
     characteristics
    0.57
     $("<
    0.57
    Characteristics
    0.56
     Characteristics
    0.55
    Properties
    0.54
     characterized
    0.52
     Properties
    0.50
     qualities
    0.50
    Activations Density 0.053%

    No Known Activations