© 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. 0-RES-MATRYOSHKA-DC
    7. 15481
    Prev
    Next
    INDEX
    Explanations

    references to a specific person's name, Mason

    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
    Referències
    -0.73
    ApiProperty
    -0.57
    tagHelperRunner
    -0.56
    biri
    -0.54
     Shell
    -0.53
     MonoBehaviour
    -0.53
    shell
    -0.52
    iras
    -0.52
    ště
    -0.52
    neme
    -0.51
    POSITIVE LOGITS
     Mason
    3.56
    Mason
    3.31
     MASON
    2.80
     mason
    2.69
    mason
    2.06
     Masonry
    1.31
     masonry
    1.24
     Masonic
    0.95
    asons
    0.90
     Freem
    0.83
    Activations Density 0.001%

    No Known Activations