© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 2468
    Prev
    Next
    INDEX
    Explanations

    positive references to the concept of being "smart."

    oai_token-act-pair · gpt-4.1-nano
    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
    Negative Logits
     AssemblyTitle
    -0.81
    XmlEnum
    -0.77
    SequentialGroup
    -0.75
     nahilalakip
    -0.74
    SharedCtor
    -0.72
    ьаж
    -0.67
    Kali
    -0.67
     InputDecoration
    -0.66
    thren
    -0.65
    FromNib
    -0.64
    POSITIVE LOGITS
     smart
    3.52
     Smart
    3.36
    smart
    3.33
    Smart
    3.25
     SMART
    2.67
    SMART
    2.67
     smarter
    2.36
     smartest
    2.31
     intelligent
    2.11
    smar
    2.03
    Activations Density 0.016%

    No Known Activations