© 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. 11697
    Prev
    Next
    INDEX
    Explanations

    comparative statements about fairness and economic principles

    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
    abestanden
    -0.75
    GrantedAuthority
    -0.72
    rrggbb
    -0.66
    ---|---|
    -0.64
    providedIn
    -0.63
     AssemblyTitle
    -0.60
    expandindo
    -0.60
    ionView
    -0.59
    SuccessListener
    -0.57
    __':
    -0.55
    POSITIVE LOGITS
     whereof
    0.55
     Trang
    0.54
    ographi
    0.53
    overall
    0.53
    ptures
    0.53
     archetype
    0.51
     punct
    0.50
    لاب
    0.50
     arche
    0.49
     overall
    0.49
    Activations Density 0.130%

    No Known Activations