© 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. 22-RES-MATRYOSHKA-DC
    7. 787
    Prev
    Next
    INDEX
    Explanations

    mentions of LGBT representation in media

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     film
    -0.99
     films
    -0.86
     movie
    -0.84
    film
    -0.83
     movies
    -0.78
     filme
    -0.78
     cinema
    -0.77
     cinemas
    -0.76
    films
    -0.73
     filmes
    -0.71
    POSITIVE LOGITS
     season
    1.32
     Season
    1.27
    season
    1.20
    Season
    1.16
     episode
    1.13
     episodes
    1.06
     SEASON
    1.06
    SEASON
    1.02
     seasons
    1.02
     sezon
    0.99
    Activations Density 0.588%

    No Known Activations