© 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. 15940
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing the totality or completeness of an attribute or condition

    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
     inquiry
    -0.92
    inquiry
    -0.86
     Inquiry
    -0.84
    Inquiry
    -0.78
     enquiry
    -0.71
     inquiries
    -0.69
    QUIRY
    -0.69
     inquired
    -0.68
     Inquiries
    -0.66
     inquiring
    -0.65
    POSITIVE LOGITS
     entirely
    1.69
    حياته
    0.89
     altogether
    0.79
    entire
    0.73
    حياتها
    0.62
     sendi
    0.62
    jsdelivr
    0.60
    precise
    0.59
    fjspx
    0.57
    styleType
    0.57
    Activations Density 0.002%

    No Known Activations