© 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. 18660
    Prev
    Next
    INDEX
    Explanations

    variations of the word "slip" and its related forms

    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
     Horowitz
    -0.77
    StartTag
    -0.73
    GenerationType
    -0.68
     Lid
    -0.68
    ссажи
    -0.66
     لص
    -0.65
     meub
    -0.65
     didik
    -0.64
    Nand
    -0.64
     Landis
    -0.62
    POSITIVE LOGITS
     Slip
    1.80
     slip
    1.74
    Slip
    1.69
    slip
    1.67
     slips
    1.54
     SLIP
    1.37
     slipping
    1.23
     slipped
    1.16
     slippage
    1.16
     slippery
    1.00
    Activations Density 0.003%

    No Known Activations