© 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. 2-RES-MATRYOSHKA-DC
    7. 3895
    Prev
    Next
    INDEX
    Explanations

    references to menu components or menu-related elements within a document

    oai_token-act-pair · gpt-4.1-nano
    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
    Hentet
    -0.58
     {?>
    -0.51
    سول
    -0.50
    Lies
    -0.45
     Guter
    -0.45
     Romains
    -0.44
     paire
    -0.43
    #!/
    -0.43
    frage
    -0.43
    pinephrine
    -0.43
    POSITIVE LOGITS
     menu
    3.47
     Menu
    3.39
    menu
    3.36
    Menu
    3.17
     menus
    2.95
     MENU
    2.91
    MENU
    2.72
     Menus
    2.63
     menú
    2.31
    menus
    2.30
    Activations Density 0.014%

    No Known Activations