© 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. 6-RES-MATRYOSHKA-DC
    7. 96
    Prev
    Next
    INDEX
    Explanations

    the word "the"

    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
     Mahomet
    -1.05
    
    -1.04
     Phry
    -1.03
     Huguen
    -0.98
     Agamemnon
    -0.94
     Shakspeare
    -0.93
     Esau
    -0.90
     Pliny
    -0.90
     Pompey
    -0.90
     Fascism
    -0.90
    POSITIVE LOGITS
     the
    2.11
     The
    1.54
    The
    1.38
     THE
    1.36
     same
    1.18
    rethe
    1.16
    the
    1.11
    enthe
    1.09
    ethe
    1.09
     entire
    1.02
    Activations Density 4.674%

    No Known Activations