© 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. 6617
    Prev
    Next
    INDEX
    Explanations

    references to the name "Marshall" or its variants

    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
    Билгалдахарш
    -0.69
     Egger
    -0.68
     يتيمه
    -0.64
    vides
    -0.60
    isure
    -0.60
    fillType
    -0.60
    RectangleBorder
    -0.59
    EDEFAULT
    -0.59
    spinning
    -0.58
    ImageContext
    -0.58
    POSITIVE LOGITS
     Marshal
    3.33
    Marshal
    2.95
     marshal
    2.92
     Marshall
    2.88
     Marsh
    2.83
     marsh
    2.81
     marshall
    2.69
    Marshall
    2.66
    Marsh
    2.63
     MARSH
    2.63
    Activations Density 0.012%

    No Known Activations