© 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. 2430
    Prev
    Next
    INDEX
    Explanations

    expressions of strong agreement or affirmation

    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
     Efq
    -0.94
    LLocation
    -0.83
    \{\\
    -0.80
    parsedMessage
    -0.80
    abestanden
    -0.80
     StatelessWidget
    -0.79
     Houſe
    -0.79
    randomUUID
    -0.78
     ſon
    -0.78
     Shaksp
    -0.78
    POSITIVE LOGITS
     indeed
    3.30
     Indeed
    2.81
    indeed
    2.81
    Indeed
    2.77
     inderdaad
    1.82
    的确
    1.45
     effectivement
    1.39
    確かに
    1.38
     infatti
    1.29
    确实
    1.20
    Activations Density 0.011%

    No Known Activations