© 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. 1489
    Prev
    Next
    INDEX
    Explanations

    mentions of specific types of experimental data or research procedures

    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
     is
    -1.59
     has
    -1.16
     Is
    -0.79
     isn
    -0.79
     è
    -0.75
     does
    -0.73
     ist
    -0.71
     IS
    -0.70
     है
    -0.70
     heeft
    -0.70
    POSITIVE LOGITS
     were
    2.70
    Were
    2.61
     Were
    2.58
    were
    2.56
     WERE
    2.38
     weren
    1.98
    weren
    1.66
     voltak
    1.45
     были
    1.41
     були
    1.38
    Activations Density 0.233%

    No Known Activations