© 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. 25629
    Prev
    Next
    INDEX
    Explanations

    references to historic or geographical entities

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ſte
    -0.81
     iſt
    -0.73
     Monfieur
    -0.73
     itſelf
    -0.72
     faſt
    -0.70
     raiſ
    -0.69
     ſever
    -0.69
     Eſ
    -0.69
     Jefus
    -0.69
    ברס
    -0.69
    POSITIVE LOGITS
    endregion
    0.66
     تانيه
    0.62
     relaj
    0.62
     Dunn
    0.59
     Sleeps
    0.57
     Goodwin
    0.56
    yanto
    0.56
    Aqua
    0.56
     Gruber
    0.56
    cox
    0.55
    Activations Density 0.038%

    No Known Activations