© 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. 17278
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names in political and historical contexts

    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
    mo
    -0.58
    Sta
    -0.53
    Z
    -0.52
    X
    -0.51
    ry
    -0.50
    Fast
    -0.49
    Med
    -0.49
    Cap
    -0.48
    la
    -0.48
    哪个
    -0.47
    POSITIVE LOGITS
    ReusableCell
    1.05
    fromnode
    1.05
     Réponses
    1.02
     ProtoMessage
    0.96
    rungsseite
    0.95
     通販
    0.93
    verwijspagina
    0.93
     AspNetCore
    0.93
    tvguidetime
    0.92
     InputDecoration
    0.91
    Activations Density 0.217%

    No Known Activations