© 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. 22-RES-MATRYOSHKA-DC
    7. 3189
    Prev
    Next
    INDEX
    Explanations

    the word "drop" and words containing "drop"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     bezeichneter
    -0.68
     onAnimation
    -0.66
    homonymie
    -0.61
     Италијани
    -0.60
     LEYENDO
    -0.59
     Rook
    -0.57
    letics
    -0.57
    enumerate
    -0.57
    QMetaType
    -0.57
    atians
    -0.56
    POSITIVE LOGITS
     drop
    1.43
     drops
    1.41
     Drop
    1.40
    drops
    1.38
    drop
    1.34
    Drop
    1.28
     DROP
    1.26
     dropped
    1.25
     Drops
    1.25
     dropping
    1.24
    Activations Density 0.027%

    No Known Activations