© 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. 4832
    Prev
    Next
    INDEX
    Explanations

    references to media content handling and manipulation within code

    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
     radio
    -1.06
     Radio
    -0.97
     mean
    -0.96
    tv
    -0.92
    radio
    -0.92
     television
    -0.90
     TV
    -0.89
    mean
    -0.86
    Radio
    -0.82
    TV
    -0.81
    POSITIVE LOGITS
    Media
    2.45
     Media
    2.39
    media
    2.38
     MEDIA
    2.34
     media
    2.33
    MEDIA
    2.11
     Medien
    1.65
    媒体
    1.52
    媒體
    1.48
     medias
    1.45
    Activations Density 0.050%

    No Known Activations