© 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. 10576
    Prev
    Next
    INDEX
    Explanations

    numerical values or quantities

    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
     وتسجيلات
    -0.81
     Dijo
    -0.69
     cirque
    -0.66
     Stratton
    -0.64
     kılıf
    -0.63
     tuta
    -0.63
    timately
    -0.62
     Monfieur
    -0.62
     fhort
    -0.61
     teardown
    -0.60
    POSITIVE LOGITS
    AnchorTagHelper
    0.83
    PreferredItem
    0.70
    elemField
    0.66
    省市镇
    0.66
    hasMoreElements
    0.65
     Meksiku
    0.63
    principalTable
    0.62
    TagHelper
    0.60
    setVerticalGroup
    0.59
    
    0.57
    Activations Density 0.004%

    No Known Activations