© 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. 7577
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing the importance of the word "everything" in various 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
     someone
    -1.20
     somebody
    -1.13
     something
    -1.05
    Someone
    -1.02
    someone
    -1.02
    Somebody
    -0.97
     alguien
    -0.96
     Someone
    -0.96
     somewhere
    -0.95
     quelqu
    -0.93
    POSITIVE LOGITS
    everything
    2.53
     Everything
    2.47
     everything
    2.45
    Everything
    2.38
     EVERYTHING
    1.89
     tudo
    1.45
    everyone
    1.22
     Tudo
    1.20
     totul
    1.20
     alles
    1.18
    Activations Density 0.025%

    No Known Activations