© 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. 1-RES-MATRYOSHKA-DC
    7. 1498
    Prev
    Next
    INDEX
    Explanations

    references to specific buildings and locations

    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
    Negative Logits
     myſelf
    -1.07
     itſelf
    -1.01
     poffible
    -0.89
     ་་
    -0.86
     raiſ
    -0.85
     leſs
    -0.85
     uſed
    -0.82
     juſt
    -0.82
     iſt
    -0.82
     Monfieur
    -0.82
    POSITIVE LOGITS
     current
    0.67
    ########.
    0.65
     ‘
    0.64
     P
    0.63
     Cha
    0.63
     per
    0.60
     H
    0.60
     '
    0.59
     way
    0.59
     following
    0.59
    Activations Density 3.998%

    No Known Activations