© 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. 2-RES-MATRYOSHKA-DC
    7. 5406
    Prev
    Next
    INDEX
    Explanations

    references to the phrase "preferred embodiment" or similar formal disclosures related to specific implementations

    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
    </em>
    -0.59
     Wirth
    -0.58
     Marche
    -0.56
    provoking
    -0.56
    findpost
    -0.54
    DoubleQuotes
    -0.54
     Joi
    -0.51
    geist
    -0.51
    snip
    -0.50
    migrationBuilder
    -0.49
    POSITIVE LOGITS
     prefer
    2.92
     Prefer
    2.92
     preferred
    2.91
     preference
    2.86
    prefer
    2.83
    Prefer
    2.77
    preferred
    2.72
     Preferred
    2.64
     Preference
    2.61
     prefers
    2.59
    Activations Density 0.052%

    No Known Activations