© 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. 1277
    Prev
    Next
    INDEX
    Explanations

    expressions of negative sentiment or criticism

    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
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.62
    KommentareTeilen
    -0.55
     nakalista
    -0.54
    PMailer
    -0.54
    Keen
    -0.54
    drücken
    -0.49
     indisponible
    -0.49
     Hano
    -0.49
    UserScript
    -0.48
    acuzzi
    -0.47
    POSITIVE LOGITS
     stop
    4.72
     Stop
    4.44
    stop
    4.34
     stops
    4.28
    Stop
    4.25
     stopped
    4.06
     STOP
    4.03
    STOP
    3.95
     Stops
    3.95
     stopping
    3.86
    Activations Density 0.261%

    No Known Activations