© 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. 3191
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     Nuss
    -0.63
    est
    -0.62
    Tembelea
    -0.59
     Walk
    -0.57
    tivism
    -0.57
     abus
    -0.55
    VSS
    -0.55
     walk
    -0.54
     present
    -0.54
    ~•
    -0.54
    POSITIVE LOGITS
    AndEndTag
    1.07
    AddTagHelper
    0.99
    awtextra
    0.82
    saraba
    0.82
     Catto
    0.80
    RegressionTest
    0.79
    jmniej
    0.79
     Arne
    0.76
    openqa
    0.76
     חיצוניים
    0.75
    Activations Density 0.662%

    No Known Activations