© 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. 0-RES-MATRYOSHKA-DC
    7. 15963
    Prev
    Next
    INDEX
    Explanations

    references to outdated or obsolete information

    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
    djangoproject
    -0.65
    клопе
    -0.62
    Externé
    -0.61
    Население
    -0.60
    DockStyle
    -0.52
    vious
    -0.51
     murah
    -0.51
     tây
    -0.51
    WithMany
    -0.50
     big
    -0.49
    POSITIVE LOGITS
     obsolete
    2.98
     outdated
    2.36
    obsolete
    2.13
     antiquated
    1.79
     archaic
    1.70
    solete
    1.69
     extinct
    1.52
    Outdated
    1.38
    Obsolete
    1.36
     stale
    1.16
    Activations Density 0.010%

    No Known Activations