© 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. 5991
    Prev
    Next
    INDEX
    Explanations

    references to personal identity

    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
    autant
    -0.82
     "))
    -0.66
     "));
    -0.63
     makl
    -0.63
    RTGC
    -0.62
    {}",
    -0.61
     %.
    -0.60
     ")
    -0.60
     uintptr
    -0.60
    %")
    -0.60
    POSITIVE LOGITS
    aarrggbb
    0.72
     Me
    0.67
     nobis
    0.63
     me
    0.61
    ofür
    0.61
     pribadi
    0.60
     defaultstate
    0.57
    InSection
    0.56
    ness
    0.55
     us
    0.54
    Activations Density 0.112%

    No Known Activations