© 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. 2-RES-MATRYOSHKA-DC
    7. 2437
    Prev
    Next
    INDEX
    Explanations

    CSS style definitions and related structure

    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
    OfBirth
    -0.67
     صوتيه
    -0.63
     estekak
    -0.60
    pragma
    -0.57
    ffre
    -0.57
    IntoConstraints
    -0.54
     GoogleFonts
    -0.52
     Fing
    -0.51
     Exacts
    -0.50
    InvalidProtocol
    -0.50
    POSITIVE LOGITS
    __':
    0.73
    AlterField
    0.71
    Javadoc
    0.64
    sizeCache
    0.62
     &___
    0.59
    __':
    0.57
     _$
    0.56
     ExecuteAsync
    0.56
    SharedDtor
    0.56
    writerow
    0.56
    Activations Density 0.248%

    No Known Activations