© 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. 0-RES-MATRYOSHKA-DC
    7. 12569
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or subscription prompts

    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
     subscription
    -0.96
     Subscription
    -0.86
     subscriptions
    -0.85
    subscription
    -0.81
     subscribers
    -0.71
     subscriber
    -0.69
    Subscription
    -0.68
     Subscriptions
    -0.65
     Subscribers
    -0.57
    subscriptions
    -0.55
    POSITIVE LOGITS
    Subscribe
    2.84
    subscribe
    2.11
     Subscribe
    1.88
    SUBSCRIBE
    1.41
     subscribe
    1.23
     SUBSCRIBE
    1.15
    ItemLayout
    0.71
    EnableWeb
    0.62
    críbete
    0.61
    reactstrap
    0.60
    Activations Density 0.001%

    No Known Activations