© 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. 3-RES-MATRYOSHKA-DC
    7. 1583
    Prev
    Next
    INDEX
    Explanations

    the word 'lead' and related words

    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
     Burrell
    -0.69
     sagrado
    -0.68
    setAccessible
    -0.67
     Devine
    -0.66
    hdashline
    -0.63
     boundaries
    -0.61
     roadside
    -0.61
     claust
    -0.60
    estic
    -0.60
     Sag
    -0.60
    POSITIVE LOGITS
     lead
    3.13
     leads
    2.88
     Lead
    2.77
    lead
    2.72
    Lead
    2.66
     Leads
    2.66
    leads
    2.56
     leading
    2.55
    Leads
    2.50
     led
    2.48
    Activations Density 0.273%

    No Known Activations