© 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. 14902
    Prev
    Next
    INDEX
    Explanations

    references to towers or tower structures

    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
     BioLib
    -0.73
    FET
    -0.66
    ={`/
    -0.65
     dục
    -0.63
     createSprite
    -0.63
    Prez
    -0.63
    meida
    -0.61
     `/
    -0.61
    IActionResult
    -0.60
     DCS
    -0.60
    POSITIVE LOGITS
     Tower
    1.73
    Tower
    1.63
     Towers
    1.63
     TOWER
    1.63
     towers
    1.60
     tower
    1.59
    tower
    1.44
    towers
    1.36
    Tow
    1.30
     Torre
    1.14
    Activations Density 0.006%

    No Known Activations