© 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. 18-RES-MATRYOSHKA-DC
    7. 1620
    Prev
    Next
    INDEX
    Explanations

    sentences describing an experiment that is repeated multiple times

    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.18.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.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    WithIOException
    -0.64
    lineTo
    -0.53
    bign
    -0.48
     joindre
    -0.47
    adto
    -0.47
    냥
    -0.47
    üglich
    -0.46
    わりに
    -0.46
    erobe
    -0.45
    arko
    -0.45
    POSITIVE LOGITS
     repeated
    2.16
     Repeated
    2.02
    repeated
    2.02
     repeatedly
    2.00
    Repeated
    1.94
     repeat
    1.86
     repeats
    1.71
     Repeat
    1.70
    Repeat
    1.69
     repeti
    1.65
    Activations Density 1.760%

    No Known Activations