© 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. 7367
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to linking stylesheets and scripts

    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
    MigrationBuilder
    -0.79
     cappuccio
    -0.75
     estacionamento
    -0.69
     ExecuteAsync
    -0.68
    IntoConstraints
    -0.67
    oustic
    -0.66
     banheiro
    -0.66
    didSet
    -0.63
     AssemblyTitle
    -0.60
     fluxo
    -0.60
    POSITIVE LOGITS
     rel
    3.45
     Rel
    2.31
    rel
    2.30
    Rel
    2.00
    REL
    1.84
     REL
    1.73
    rels
    1.41
     relish
    1.35
    rela
    1.30
     relati
    1.21
    Activations Density 0.012%

    No Known Activations