© 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. 181
    Prev
    Next
    INDEX
    Explanations

    the word "test" and related words such as "demonstrated"

    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
    aktery
    -0.88
    клопе
    -0.85
    AsUp
    -0.81
     uintptr
    -0.78
    StringCopy
    -0.75
    VIAF
    -0.75
     gefü
    -0.75
    gatsby
    -0.75
     arşivlendi
    -0.74
     rospy
    -0.74
    POSITIVE LOGITS
     test
    2.05
     Test
    2.02
     tests
    1.96
    Test
    1.92
     TEST
    1.89
     Tests
    1.89
    test
    1.85
    TEST
    1.82
     testing
    1.75
    Tests
    1.69
    Activations Density 0.641%

    No Known Activations