© 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. 1315
    Prev
    Next
    INDEX
    Explanations

    references to exceptional or noteworthy cases

    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
    TagMode
    -0.63
     GoogleFonts
    -0.60
     <<<<<<<<<<<<<<
    -0.58
    Jereo
    -0.55
    rigley
    -0.55
    KommentareTeilen
    -0.53
     allegedly
    -0.50
    creativecommons
    -0.50
     expressed
    -0.50
    urlpatterns
    -0.50
    POSITIVE LOGITS
     exception
    4.19
     exceptions
    3.64
     Exception
    3.47
    exception
    3.30
     Exceptions
    3.30
    Exception
    3.16
     excep
    3.02
     EXCEPT
    3.02
     excepción
    3.00
    EXCEPT
    2.97
    Activations Density 0.196%

    No Known Activations