© 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. 2592
    Prev
    Next
    INDEX
    Explanations

    expressions of strong affection or love

    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
     liked
    -1.21
     disliked
    -1.09
     Liked
    -0.94
     preferred
    -0.94
    liked
    -0.90
     dislikes
    -0.89
    preferred
    -0.77
     liking
    -0.74
     enjoyed
    -0.73
     admired
    -0.71
    POSITIVE LOGITS
     love
    1.59
     Love
    1.55
    Love
    1.51
    love
    1.47
     LOVE
    1.24
    LOVE
    1.16
     liefde
    1.00
     любовь
    0.93
     tình
    0.85
     любов
    0.85
    Activations Density 0.012%

    No Known Activations