© 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. 32
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs like 'can', 'could', 'will', 'would', 'have', and 'had', often alongside 'to'

    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
     jLabel
    -0.89
     snoring
    -0.77
     niega
    -0.76
     asciug
    -0.75
     cocks
    -0.72
     Jefus
    -0.71
     couverts
    -0.71
     tecnici
    -0.71
     dries
    -0.70
     cools
    -0.70
    POSITIVE LOGITS
     be
    1.63
     can
    1.17
     have
    1.16
     could
    1.16
     would
    1.12
     will
    1.09
     should
    1.08
     pueda
    1.00
     make
    1.00
    ที่จะ
    1.00
    Activations Density 4.536%

    No Known Activations