© 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. 23294
    Prev
    Next
    INDEX
    Explanations

    the term "proper" and its variants, emphasizing standards or correctness

    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
     iCloud
    -0.99
    Württemberg
    -0.96
    addCriterion
    -0.92
    ethene
    -0.91
     Walkover
    -0.91
    atility
    -0.90
    retweeted
    -0.88
    brities
    -0.87
    riott
    -0.86
     Tahu
    -0.86
    POSITIVE LOGITS
     Norwood
    0.73
    ly
    0.69
     Properly
    0.69
     properly
    0.66
    maßen
    0.66
    properly
    0.65
     Dani
    0.63
    Proper
    0.62
    mor
    0.61
     mehrerer
    0.60
    Activations Density 0.013%

    No Known Activations