© 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. 3-RES-MATRYOSHKA-DC
    7. 1076
    Prev
    Next
    INDEX
    Explanations

    the phrase "United States"

    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
    évaluateur
    -0.80
     Orissa
    -0.76
     Meksiku
    -0.74
    NameInMap
    -0.73
     Roskov
    -0.71
     Schuyler
    -0.69
     toscana
    -0.69
     Cuckoo
    -0.69
     Oregon
    -0.68
    Oregon
    -0.67
    POSITIVE LOGITS
     United
    3.16
    United
    2.97
     UNITED
    2.52
    UNITED
    2.36
    united
    2.06
     united
    1.95
     Vereinigten
    1.57
     Verenigde
    1.41
     Utd
    1.32
     Vereinigte
    1.23
    Activations Density 0.030%

    No Known Activations