© 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. 23789
    Prev
    Next
    INDEX
    Explanations

    demographic information regarding age and gender

    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
    دانشنامهٔ
    -0.91
    ArrowToggle
    -0.85
     greateſt
    -0.78
     لينك
    -0.77
     Jefus
    -0.75
    orphaned
    -0.72
     faſt
    -0.72
     iſt
    -0.70
     Exacts
    -0.70
     pngtree
    -0.70
    POSITIVE LOGITS
     ste
    0.50
     trade
    0.49
     Cy
    0.46
     and
    0.46
    gonic
    0.44
     who
    0.44
     contre
    0.44
     in
    0.44
     cy
    0.44
     &
    0.43
    Activations Density 0.026%

    No Known Activations