© 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. 23115
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names or initials associated with individuals in academic or scientific 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
     betweenstory
    -0.73
    kháu
    -0.72
     >=",
    -0.71
    exitRule
    -0.71
    featureID
    -0.70
     itſelf
    -0.66
     kasarigan
    -0.64
     للمعارف
    -0.63
     Theſe
    -0.63
     Efq
    -0.63
    POSITIVE LOGITS
    ͡
    0.60
    aryen
    0.58
    ocities
    0.58
    出版年
    0.57
     []:
    0.56
    )$_
    0.56
     Wikimédia
    0.56
     *__
    0.55
     [*]
    0.54
    fortawesome
    0.54
    Activations Density 0.027%

    No Known Activations