© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4768
    Prev
    Next
    INDEX
    Explanations

    references to expressions of heartfelt emotion or significance

    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
     Cards
    -1.74
     Card
    -1.73
     card
    -1.70
     cards
    -1.70
    Card
    -1.59
    Cards
    -1.58
     CARD
    -1.57
    card
    -1.52
    cards
    -1.51
     CARDS
    -1.43
    POSITIVE LOGITS
     heart
    2.58
    heart
    2.14
     Heart
    2.11
     HEART
    2.03
    Heart
    2.02
    HEART
    1.88
     hearts
    1.63
     corazón
    1.56
     coração
    1.46
    hearts
    1.40
    Activations Density 0.025%

    No Known Activations