© 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. 4041
    Prev
    Next
    INDEX
    Explanations

    references to news broadcasts and related terminology

    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
    -1.01
    expandindo
    -0.94
    ukone
    -0.87
     smtplib
    -0.84
     NUKAT
    -0.83
    клопе
    -0.83
    RenderAtEndOf
    -0.83
     Nieuws
    -0.82
     paparazzi
    -0.82
     ſche
    -0.81
    POSITIVE LOGITS
     broadcast
    2.86
    broadcast
    2.56
     Broadcast
    2.45
    Broadcast
    2.42
     broadcasts
    2.22
     broadcasting
    1.96
     Broadcasting
    1.59
     broadcasters
    1.59
    BROAD
    1.39
     broadcaster
    1.37
    Activations Density 0.012%

    No Known Activations