© 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. 30594
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, particularly "Alan" and variations of "Allen."

    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
     Majefty
    -1.31
    Personensuche
    -1.23
     FetchType
    -1.15
    ंदीखरीदारी
    -1.13
     ivelany
    -1.13
     myſelf
    -1.09
    بوابة
    -1.07
     ISNI
    -1.07
     itſelf
    -1.04
     greateſt
    -1.03
    POSITIVE LOGITS
     Alan
    1.42
     Allen
    1.35
    Alan
    1.14
     alan
    1.03
    Allen
    1.02
     ALAN
    0.94
    alan
    0.87
     ALLEN
    0.83
     Allan
    0.81
    ALAN
    0.81
    Activations Density 0.004%

    No Known Activations