© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 32
    Prev
    Next
    INDEX
    Explanations

    references to the Reuben sandwich or related historical origin stories

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.78
     itſelf
    -1.70
     ―――――
    -1.67
    ſelf
    -1.65
     pleaſure
    -1.64
     auffi
    -1.62
    <bos>
    -1.61
    ſelves
    -1.59
     faſt
    -1.59
     ſche
    -1.58
    POSITIVE LOGITS
     
    2.38
     "
    1.20
     “
    1.13
      
    1.12
     $
    1.09
     I
    1.05
     (
    1.05
     C
    1.00
     B
    1.00
     T
    0.99
    Activations Density 3.767%

    No Known Activations