© 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. 22422
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically 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
     Hild
    -0.68
    hift
    -0.67
    Kira
    -0.65
     Sarg
    -0.64
     soeur
    -0.63
     chipping
    -0.63
    Becker
    -0.63
    1
    -0.62
     bic
    -0.62
     petal
    -0.61
    POSITIVE LOGITS
     POU
    1.20
     Vou
    1.16
     LOU
    1.14
     Cou
    1.13
     Gou
    1.13
     Kou
    1.13
     Cougars
    1.13
     rou
    1.12
     gou
    1.10
     MOU
    1.08
    Activations Density 0.157%

    No Known Activations