© 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. 192
    Prev
    Next
    INDEX
    Explanations

    words that have a high correlation to a particular topic, with the most activated topic being characters in a science-fiction Japanese show

    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
    quelize
    -0.93
     Lawler
    -0.85
    aarrggbb
    -0.82
    adalajara
    -0.80
    ergies
    -0.80
     Minerva
    -0.79
     DriverManager
    -0.79
     TableColumn
    -0.78
    ilies
    -0.78
    derry
    -0.77
    POSITIVE LOGITS
    ting
    1.15
    tttt
    1.13
    tt
    1.07
    tet
    1.04
    ttt
    1.01
    thet
    1.01
    t
    0.98
    lit
    0.97
    ent
    0.96
    lt
    0.93
    Activations Density 7.334%

    No Known Activations