© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 751
    Prev
    Next
    INDEX
    Explanations

    a three-letter prefix "Sw" followed by another letter in many different words.

    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.18.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.18.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
    dflare
    -0.68
     '\\;'
    -0.66
    ContentAsync
    -0.65
     ModelExpression
    -0.65
    ).]
    -0.63
    IntoConstraints
    -0.63
    цездатний
    -0.62
    ="<?=$
    -0.61
     piedi
    -0.61
    Parcelize
    -0.60
    POSITIVE LOGITS
     Sw
    1.37
     sw
    1.35
    Sw
    1.30
    sw
    1.12
     SW
    1.07
     SWE
    0.97
    SW
    0.94
     Swanson
    0.93
    Swish
    0.93
     Swa
    0.90
    Activations Density 0.214%

    No Known Activations