© 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. 21002
    Prev
    Next
    INDEX
    Explanations

    phrases comparing or referencing other objects or phenomena

    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
     архивлан
    -0.67
     jLabel
    -0.64
    \{\\
    -0.60
     AssemblyTitle
    -0.58
    moveToFirst
    -0.57
    ↩
    -0.56
    }}</
    -0.55
    mainAxisSize
    -0.54
     Basically
    -0.54
     ifølge
    -0.53
    POSITIVE LOGITS
    swire
    0.73
    complexContent
    0.72
    bewerken
    0.65
     cherchés
    0.63
    脚注の使い方
    0.62
    saraba
    0.60
    
    0.60
     Kram
    0.59
    OGND
    0.58
     relâche
    0.58
    Activations Density 0.003%

    No Known Activations