© 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. 1073
    Prev
    Next
    INDEX
    Explanations

    the word "deep" followed by another word, along with related terms like "depths".

    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
    RegistryLite
    -0.96
    antMatchers
    -0.93
    AccessorTable
    -0.85
     Roskov
    -0.85
    RectangleBorder
    -0.83
    urlpatterns
    -0.83
    MessageTagHelper
    -0.81
    MeasureSpec
    -0.75
    queryInterface
    -0.75
    KURZBESCHREIBUNG
    -0.74
    POSITIVE LOGITS
     deep
    2.34
     depth
    2.09
    deep
    2.09
     Deep
    2.09
     DEEP
    2.09
    Deep
    2.05
     deeper
    1.99
     deepest
    1.98
    DEEP
    1.95
     Depth
    1.94
    Activations Density 0.402%

    No Known Activations