© 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. 3-RES-MATRYOSHKA-DC
    7. 1791
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets, places, names, and possibly some Mandarin 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
    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
     mukana
    -0.81
     Svizzera
    -0.73
    Hutch
    -0.71
    drücke
    -0.68
     Hutton
    -0.67
    bonucle
    -0.66
     Huston
    -0.64
     Franke
    -0.64
    Benny
    -0.62
     Ludo
    -0.62
    POSITIVE LOGITS
     IAA
    0.99
     Iain
    0.95
     Jai
    0.93
    Iain
    0.88
    AIS
    0.88
     DIA
    0.82
     UIP
    0.81
     Meas
    0.80
     Lait
    0.79
     Tait
    0.79
    Activations Density 4.238%

    No Known Activations