© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 30866
    Prev
    Next
    INDEX
    Explanations

    demographic information related to 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
    Negative Logits
     aged
    -0.64
    aged
    -0.63
    dersfield
    -0.63
    getAge
    -0.63
     ")");
    -0.60
    AGED
    -0.58
     edad
    -0.54
    ocino
    -0.54
    ')"
    -0.54
     invokingState
    -0.53
    POSITIVE LOGITS
    RegressionTest
    0.73
    دانشنامهٔ
    0.65
     estekak
    0.63
     ſche
    0.61
     purpoſe
    0.59
    queryInterface
    0.58
    Recu
    0.57
    errHandler
    0.55
    RenderAtEndOf
    0.55
     Monfieur
    0.54
    Activations Density 0.010%

    No Known Activations