© 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. 2553
    Prev
    Next
    INDEX
    Explanations

    the term "keyword"

    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
    openhague
    -0.66
     graphene
    -0.60
    k
    -0.59
    FFER
    -0.58
    kPa
    -0.57
     McDermott
    -0.56
    WebVitals
    -0.56
     cham
    -0.54
    ATCC
    -0.54
    Niels
    -0.54
    POSITIVE LOGITS
     keyword
    2.66
    Keyword
    2.61
     keywords
    2.55
     Keyword
    2.50
    keyword
    2.36
     Keywords
    2.36
    keywords
    2.30
    Keywords
    2.20
    KEYWORD
    1.81
    KEYWORDS
    1.61
    Activations Density 0.009%

    No Known Activations