© 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. 1-RES-MATRYOSHKA-DC
    7. 967
    Prev
    Next
    INDEX
    Explanations

    words indicating intelligence, wisdom, or strategic insight

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.84
     Bork
    -0.66
    ABASES
    -0.64
    Personensuche
    -0.62
    hedrals
    -0.59
    Microkernel
    -0.59
    örung
    -0.59
    orial
    -0.57
    XmlEnum
    -0.56
    losseum
    -0.55
    POSITIVE LOGITS
     smart
    2.97
    smart
    2.66
     intelligent
    2.63
     wise
    2.61
     Smart
    2.52
    Smart
    2.50
     inteligente
    2.44
     smarter
    2.36
     Wise
    2.33
     clever
    2.25
    Activations Density 0.885%

    No Known Activations