© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5047
    Prev
    Next
    INDEX
    Explanations

    references to small screen sizes or device categories

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JspWriter
    -0.69
    PreInfinity
    -0.67
    djangoproject
    -0.62
     onPostExecute
    -0.60
     Gregorian
    -0.60
    Cass
    -0.59
    //*[@
    -0.59
    TCS
    -0.59
    makeConstraints
    -0.58
     Satt
    -0.57
    POSITIVE LOGITS
    sm
    3.06
     sm
    2.83
     SM
    2.81
    SM
    2.73
     Sm
    2.50
    Sm
    2.42
     SMI
    1.43
     Smo
    1.38
     smo
    1.30
     Smol
    1.23
    Activations Density 0.037%

    No Known Activations