© 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. 6-RES-MATRYOSHKA-DC
    7. 578
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are likely proper names or IDs, especially acronyms, company names, and surnames

    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
    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
    й
    -1.07
    e
    -0.89
    一个
    -0.88
    iwa
    -0.84
     Kirs
    -0.83
    Gott
    -0.81
    йки
    -0.81
     Tats
    -0.81
    i
    -0.81
    tling
    -0.80
    POSITIVE LOGITS
     suivie
    0.89
    gnügen
    0.86
    に
    0.85
     Lynd
    0.85
     nationaux
    0.84
     Kendal
    0.84
    Халык
    0.83
     moeite
    0.82
     soeur
    0.82
     Landis
    0.81
    Activations Density 5.515%

    No Known Activations