© 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. 10730
    Prev
    Next
    INDEX
    Explanations

    words indicating worsening or increase in severity

    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
    ITUD
    -0.47
    ú
    -0.46
    DBNull
    -0.45
    NewUrlParser
    -0.45
     Normdatei
    -0.45
    čník
    -0.44
    givings
    -0.43
     AssemblyCompany
    -0.42
    ifeng
    -0.42
    有
    -0.41
    POSITIVE LOGITS
     worsening
    2.61
     worsen
    2.42
     worsened
    2.14
     aggra
    1.84
     wors
    1.75
    wors
    1.69
     aggravate
    1.48
     Wors
    1.42
     intensify
    1.40
     exacerbate
    1.36
    Activations Density 0.002%

    No Known Activations