© 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. 3300
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
    pi
    -0.55
     Hank
    -0.49
     ύ
    -0.45
     pi
    -0.43
    aarrggbb
    -0.42
    жа
    -0.41
    PI
    -0.41
    skyl
    -0.41
    цин
    -0.40
    dflare
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.81
    IVEREF
    0.72
     referenties
    0.69
     Wikimedijinoj
    0.68
    BagConstraints
    0.64
    nuit
    0.63
     мәкал
    0.63
     exponent
    0.63
    tanleria
    0.62
    seamnă
    0.62
    Activations Density 0.213%

    No Known Activations