© 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. 6248
    Prev
    Next
    INDEX
    Explanations

    references to records and legal proceedings

    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
    profen
    -0.61
    llary
    -0.56
    brium
    -0.53
     HttpHeaders
    -0.53
    bastien
    -0.51
     GeoNames
    -0.50
    Shh
    -0.50
    urlopen
    -0.50
    utc
    -0.49
    انگلیسی
    -0.49
    POSITIVE LOGITS
    Portail
    1.05
     of
    0.94
     transférez
    0.80
     GlobalKey
    0.78
     beginnetje
    0.74
     BoxFit
    0.72
     nahilalakip
    0.72
     MessageBoxIcon
    0.71
    setDo
    0.71
    Portály
    0.70
    Activations Density 1.047%

    No Known Activations