© 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. 7743
    Prev
    Next
    INDEX
    Explanations

    expressions of intense negative emotions, particularly hatred and anger

    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
    ChromeDriver
    -0.60
    psies
    -0.58
    KURZBESCHREIBUNG
    -0.58
    telser
    -0.57
    zzleHttp
    -0.55
    verwijspagina
    -0.53
     Risiken
    -0.52
     disambiguazione
    -0.52
     pause
    -0.51
     spann
    -0.51
    POSITIVE LOGITS
     hate
    1.84
     anger
    1.84
     hatred
    1.77
     resentment
    1.64
     angry
    1.60
     Anger
    1.55
     HATE
    1.55
     hates
    1.55
     Hate
    1.51
    Anger
    1.51
    Activations Density 0.405%

    No Known Activations