© 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. 1525
    Prev
    Next
    INDEX
    Explanations

    negative evaluations or expressions of poor quality or harm

    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
    SuccessListener
    -0.64
     breakthrough
    -0.59
    PositiveButton
    -0.57
    NonNull
    -0.54
    astify
    -0.54
    amaño
    -0.54
     removeAll
    -0.52
     antidote
    -0.50
    ConstraintMaker
    -0.50
     respite
    -0.50
    POSITIVE LOGITS
     bad
    2.83
    bad
    2.58
    Bad
    2.55
     Bad
    2.41
     poor
    2.34
     BAD
    2.20
     mauvais
    2.19
     mauvaise
    2.16
    Poor
    2.14
    poor
    2.11
    Activations Density 0.832%

    No Known Activations