© 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. 1324
    Prev
    Next
    INDEX
    Explanations

    references to entities or concepts that are explicitly identified as "known."

    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
     understand
    -0.96
     understanding
    -0.93
    understand
    -0.90
     understands
    -0.88
    understanding
    -0.85
     Understand
    -0.85
     realize
    -0.81
     realise
    -0.75
    migrationBuilder
    -0.75
    knowledge
    -0.75
    POSITIVE LOGITS
     known
    3.78
    known
    3.34
     Known
    3.22
    Known
    3.16
     KNOWN
    3.02
     conocido
    2.34
     conocida
    2.33
     conhecido
    2.30
     conhecida
    2.23
    KNOWN
    2.20
    Activations Density 0.144%

    No Known Activations