© 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. 3558
    Prev
    Next
    INDEX
    Explanations

    references to legal rules and statutory language

    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
    帖最后由
    -0.65
    MockMvc
    -0.52
    ).]
    -0.49
    aronder
    -0.45
     mete
    -0.41
    Aiheesta
    -0.41
    aibo
    -0.40
    HomeAsUpEnabled
    -0.40
     hashCode
    -0.39
     họ
    -0.39
    POSITIVE LOGITS
    bootstrapcdn
    0.80
     propOrder
    0.70
    IUrlHelper
    0.70
    GEBURTSDATUM
    0.68
    ftagPool
    0.68
     lenker
    0.65
    QMetaType
    0.65
     OMITBAD
    0.65
    orable
    0.63
    MigrationBuilder
    0.63
    Activations Density 0.075%

    No Known Activations