© 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. 1505
    Prev
    Next
    INDEX
    Explanations

    areas of whitespace

    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
     Houſe
    -1.34
     purpoſe
    -1.33
     ―――――
    -1.28
     ſche
    -1.26
     houſe
    -1.25
     Efq
    -1.23
     Diſ
    -1.22
     ſta
    -1.20
     Reſ
    -1.19
     Monfieur
    -1.19
    POSITIVE LOGITS
       
    1.81
    קישורים
    0.96
      
    0.88
    mtext
    0.77
    -\
    0.72
     ’
    0.72
    FSA
    0.61
    drawiam
    0.60
     LLP
    0.60
     Loomis
    0.60
    Activations Density 0.184%

    No Known Activations