© 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. 17088
    Prev
    Next
    INDEX
    Explanations

    mentions of specific authors or works in a review context

    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
     of
    -0.53
    .
    -0.52
    <eos>
    -0.46
     in
    -0.46
     at
    -0.45
    -
    -0.45
     des
    -0.45
    del
    -0.42
    ↵↵
    -0.41
     los
    -0.41
    POSITIVE LOGITS
     nahilalakip
    1.18
     CreateTagHelper
    1.16
     للمعارف
    1.12
     estekak
    1.11
     gynhyrchwyd
    1.09
     فريبيس
    1.08
    expandindo
    1.07
    saraba
    1.03
     transfieras
    1.03
     كومونز
    1.02
    Activations Density 0.220%

    No Known Activations