© 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. 5632
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person's name

    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
     AMT
    -0.80
    ulemon
    -0.80
    interopRequire
    -0.76
    MessageTagHelper
    -0.74
     Réponses
    -0.72
     estekak
    -0.69
    igshid
    -0.68
     MTT
    -0.67
    ValueStyle
    -0.67
    WebControls
    -0.66
    POSITIVE LOGITS
     Tom
    3.30
    Tom
    3.16
     tom
    3.05
     TOM
    2.72
    tom
    2.58
    TOM
    2.41
     Toms
    2.06
    toms
    1.76
    tomo
    1.48
     tomo
    1.45
    Activations Density 0.054%

    No Known Activations