© 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. 7469
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "the most" or "the ever" in superlative contexts

    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
     always
    -0.90
    always
    -0.88
     Always
    -0.83
     never
    -0.82
    Always
    -0.79
     Never
    -0.71
    never
    -0.69
    Never
    -0.67
     跳转至
    -0.62
     ALWAYS
    -0.58
    POSITIVE LOGITS
     ever
    2.92
    ever
    2.41
     EVER
    2.28
    Ever
    2.28
     Ever
    2.25
    EVER
    2.00
     ooit
    1.48
     jemals
    1.26
     euer
    1.02
     pernah
    0.96
    Activations Density 0.009%

    No Known Activations