© 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. 15729
    Prev
    Next
    INDEX
    Explanations

    references to identifying the source of evidence or information in a context

    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
    
    -0.78
    脚注の使い方
    -0.73
     חיצוניים
    -0.71
     himo
    -0.70
    WebVitals
    -0.69
     للمعارف
    -0.68
    issauga
    -0.68
     bezeichneter
    -0.67
    AndEndTag
    -0.66
    +#+
    -0.63
    POSITIVE LOGITS
     intentos
    0.47
     lo
    0.47
     tepat
    0.45
    principalTable
    0.45
     émer
    0.44
     neige
    0.44
     terminé
    0.44
     именно
    0.43
     порядке
    0.43
     humanas
    0.43
    Activations Density 0.285%

    No Known Activations