© 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. 23285
    Prev
    Next
    INDEX
    Explanations

    names, particularly Korean names

    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
     faſt
    -0.83
    endphp
    -0.82
    ftance
    -0.82
    σιμοποι
    -0.72
     Efq
    -0.72
    WebElementEntity
    -0.71
     itſelf
    -0.71
     Theſe
    -0.69
    jsonwebtoken
    -0.69
     iſt
    -0.68
    POSITIVE LOGITS
     or
    0.43
    ellido
    0.43
     о
    0.42
     o
    0.40
     Roskov
    0.40
    ScopeManager
    0.40
     Irlanda
    0.39
     traite
    0.38
     v
    0.38
     all
    0.38
    Activations Density 0.033%

    No Known Activations