© 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. 6196
    Prev
    Next
    INDEX
    Explanations

    references to television programs, specifically those emphasizing the word "TV"

    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
    AddTagHelper
    -0.84
     media
    -0.84
    /*---
    -0.83
     PRESS
    -0.83
    news
    -0.82
     MEDIA
    -0.80
     press
    -0.78
    Media
    -0.78
    EndProject
    -0.78
    News
    -0.77
    POSITIVE LOGITS
     TV
    2.66
    TV
    2.42
     tv
    2.30
     television
    2.17
    tv
    2.11
     Television
    2.00
     Tv
    1.97
    Television
    1.89
    Tv
    1.80
     TVs
    1.79
    Activations Density 0.025%

    No Known Activations