© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 405
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty or conditions that define contexts in a complex argument

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     the
    -0.35
     and
    -0.35
     Sunday
    -0.30
     Senado
    -0.28
     Tuesday
    -0.28
     adult
    -0.27
    ,
    -0.27
     Wednesday
    -0.27
     caoutchouc
    -0.27
     Islam
    -0.27
    POSITIVE LOGITS
     Chwiliwch
    0.75
    PreferredItem
    0.75
     мәкал
    0.69
    iſen
    0.68
     مشين
    0.67
    mpagne
    0.65
    ⤒
    0.65
     yym
    0.64
    gucig
    0.63
     BrowserModule
    0.62
    Activations Density 6.172%

    No Known Activations