© 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. 3047
    Prev
    Next
    INDEX
    Explanations

    publishing locations and entities

    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
     Sorg
    -0.49
    rat
    -0.45
    容
    -0.44
    ligencia
    -0.44
     sung
    -0.43
    হ
    -0.43
     tròn
    -0.42
     ویکی
    -0.42
    AccessException
    -0.42
    Chapter
    -0.41
    POSITIVE LOGITS
     Press
    0.84
     الرياضيه
    0.82
    Press
    0.75
     press
    0.75
    >{@
    0.66
     MainAxisSize
    0.65
    ArrowToggle
    0.64
     старости
    0.64
     PRESS
    0.63
    TagMode
    0.62
    Activations Density 0.052%

    No Known Activations