© 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. 2006
    Prev
    Next
    INDEX
    Explanations

    references to gender, particularly focusing on men and male-related themes

    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
     snippetHide
    -0.91
    ']")
    -0.85
    źródło
    -0.78
    UnsafeEnabled
    -0.77
     intptr
    -0.77
    IsContent
    -0.74
     صوتيه
    -0.72
    躇
    -0.71
    tvguidetime
    -0.71
     للاسماء
    -0.71
    POSITIVE LOGITS
     Men
    1.27
     men
    1.22
     Male
    1.13
     male
    1.09
    Men
    1.05
    Male
    1.04
     MEN
    1.04
     Männer
    1.01
     Gentlemen
    0.97
     Women
    0.96
    Activations Density 0.561%

    No Known Activations