© 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. 2918
    Prev
    Next
    INDEX
    Explanations

    first-person anecdotes

    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
    Not in Any Lists

    No Comments

    Negative Logits
     apapun
    -0.63
     anything
    -0.62
     tetap
    -0.57
    それでも
    -0.57
     continuare
    -0.56
    後は
    -0.56
     weiterhin
    -0.56
     seguirá
    -0.56
     дальше
    -0.56
     autant
    -0.54
    POSITIVE LOGITS
     overheard
    1.09
     accidentally
    1.01
     recently
    1.00
    recently
    0.92
    偶然
    0.90
    ImageContext
    0.88
    某
    0.88
     CURIAM
    0.86
     случайно
    0.85
     autorytatywna
    0.85
    Activations Density 0.895%

    No Known Activations