© 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. 26175
    Prev
    Next
    INDEX
    Explanations

    references to advertisements and their impact on media representation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    endphp
    -0.82
    StoryboardSegue
    -0.66
     bezeichneter
    -0.65
    specialchars
    -0.54
     INSEE
    -0.52
     שוליים
    -0.52
    endpush
    -0.51
     angekommen
    -0.50
     enfans
    -0.50
    وانید
    -0.49
    POSITIVE LOGITS
     advertising
    0.79
     campaigns
    0.76
     rekla
    0.74
     campaign
    0.74
     commercials
    0.67
    vertising
    0.65
     Campaigns
    0.63
     ads
    0.61
     billboards
    0.60
    Campaign
    0.57
    Activations Density 0.055%

    No Known Activations