© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 5437
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to sexual orientation and LGBTQ+ identities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    JEL
    -0.65
    ViewFeatures
    -0.59
    <%
    -0.59
    Vidite
    -0.58
    Portale
    -0.57
    migrationBuilder
    -0.57
    //*
    -0.56
    rifuge
    -0.56
     ddelweddau
    -0.54
     Halliday
    -0.54
    POSITIVE LOGITS
     homosexual
    1.38
     gay
    1.23
     GAY
    1.22
     homosexuality
    1.20
     Gay
    1.19
    Gay
    1.17
    gay
    1.11
     gays
    1.11
    osexual
    0.99
     homophobic
    0.98
    Activations Density 0.024%

    No Known Activations