© 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. 32593
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or longing

    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
    migrationBuilder
    -0.93
     mukaan
    -0.91
     BoxDecoration
    -0.89
    positorio
    -0.82
    addPreferredGap
    -0.79
     Pelop
    -0.79
     Nader
    -0.79
     outlander
    -0.78
    cyd
    -0.77
     InputDecoration
    -0.76
    POSITIVE LOGITS
     Wish
    0.86
    Wish
    0.85
    wish
    0.85
     WISH
    0.82
     wish
    0.76
     Wis
    0.65
     kê
    0.65
    WISH
    0.63
     ti
    0.62
     Wishes
    0.61
    Activations Density 0.006%

    No Known Activations