© 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. 1941
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially names of people, places, and currencies, and possibly also some related concepts or abbreviations.

    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
     Sitten
    -0.69
    ContextHolder
    -0.68
     PSS
    -0.67
     Chengdu
    -0.66
     GenerationType
    -0.65
    Сайт
    -0.65
     DSS
    -0.64
     CITES
    -0.64
     Charlemagne
    -0.62
     Dorian
    -0.62
    POSITIVE LOGITS
    jab
    1.20
     Kub
    1.20
    rab
    1.19
    LAB
    1.19
     Mab
    1.19
     Dab
    1.19
    jeb
    1.18
     LAB
    1.16
     Jab
    1.16
     Wab
    1.16
    Activations Density 1.880%

    No Known Activations