© 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. 3-RES-MATRYOSHKA-DC
    7. 2588
    Prev
    Next
    INDEX
    Explanations

    the name Johnson in legal documents

    oai_token-act-pair · gemini-2.0-flash
    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
     Beres
    -0.80
    بوابة
    -0.72
    pyplot
    -0.69
     Maus
    -0.65
     Mau
    -0.62
     Gerr
    -0.61
     inves
    -0.57
    رياض
    -0.57
     Cale
    -0.56
     ברו
    -0.56
    POSITIVE LOGITS
     Johnson
    3.11
    Johnson
    2.98
     JOHNSON
    2.88
     johnson
    2.77
    johnson
    2.31
     Jonson
    1.68
    JOH
    1.60
    NSON
    1.59
     Johns
    1.28
    Johns
    1.17
    Activations Density 0.004%

    No Known Activations