© 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. 3279
    Prev
    Next
    INDEX
    Explanations

    the first syllable of names

    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
    RenderAtEndOf
    -0.96
    ly
    -0.75
    mente
    -0.72
    ۰
    -0.72
    に
    -0.72
    是
    -0.70
    Hozzáférés
    -0.70
    p
    -0.69
    fully
    -0.67
    errHandler
    -0.66
    POSITIVE LOGITS
    e
    0.61
    es
    0.57
    a
    0.52
    os
    0.50
    cho
    0.46
    pportun
    0.46
    ols
    0.45
    ه
    0.45
    orna
    0.45
     dõi
    0.45
    Activations Density 0.385%

    No Known Activations