© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4172
    Prev
    Next
    INDEX
    Explanations

    references to subscription-related words

    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
     שוליים
    -0.82
     plagio
    -0.78
    WebElementEntity
    -0.78
     NSCoder
    -0.75
     ujednoznacz
    -0.72
     saites
    -0.71
    حوالہ
    -0.70
    ESSOR
    -0.69
    ValueStyle
    -0.69
    NameInMap
    -0.68
    POSITIVE LOGITS
     subscription
    3.05
     subscribe
    2.75
     subscriptions
    2.75
     Subscription
    2.64
    subscription
    2.56
     subscribed
    2.48
    Subscription
    2.45
     Subscriptions
    2.39
     subscribing
    2.36
     subscri
    2.28
    Activations Density 0.090%

    No Known Activations