© 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. 12-RES-MATRYOSHKA-DC
    7. 30445
    Prev
    Next
    INDEX
    Explanations

    mentions of gender inequality and representation in various contexts

    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
     ethnicity
    -0.63
     patients
    -0.62
     ethnic
    -0.59
     race
    -0.58
     races
    -0.56
    ыгана
    -0.55
    ebaran
    -0.55
    scriptcase
    -0.53
     patient
    -0.52
    Становништво
    -0.51
    POSITIVE LOGITS
     الحره
    0.66
    HomeAsUpEnabled
    0.60
     BoxFit
    0.58
    AnchorStyles
    0.57
    DockStyle
    0.55
     Zelanda
    0.55
     Hatt
    0.55
    findpost
    0.53
     CascadeType
    0.53
    Жен
    0.52
    Activations Density 0.020%

    No Known Activations