© 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. 14382
    Prev
    Next
    INDEX
    Explanations

    the emphasis on low-budget television production techniques and the portrayal of diversity in media content

    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
    Actress
    -0.75
     Actress
    -0.75
     rapper
    -0.73
    Actor
    -0.71
     Actor
    -0.66
    Singer
    -0.63
     actress
    -0.63
    actor
    -0.61
     singer
    -0.60
    waarde
    -0.59
    POSITIVE LOGITS
     actors
    1.63
     acteurs
    1.12
     Actors
    0.98
     actores
    0.97
    Actors
    0.85
     ***!
    0.72
    actors
    0.72
    DeleteBehavior
    0.70
    enumii
    0.66
    NameInMap
    0.65
    Activations Density 0.001%

    No Known Activations