© 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. 0-RES-MATRYOSHKA-DC
    7. 14392
    Prev
    Next
    INDEX
    Explanations

    logical or circuit-related terminology, especially associated with circuit structure, gates, or specific circuit types

    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
    StoryboardSegue
    -0.81
     betweenstory
    -0.66
    arrête
    -0.63
     guil
    -0.62
     householder
    -0.60
    IUrlHelper
    -0.58
     kolej
    -0.57
     Bernardino
    -0.56
    alnız
    -0.56
     électro
    -0.56
    POSITIVE LOGITS
     Handicap
    0.81
    CREAT
    0.79
     alo
    0.78
     handicap
    0.78
    ctable
    0.75
    ulfide
    0.71
    Personensuche
    0.69
    SequentialGroup
    0.68
     sputtering
    0.65
    cranial
    0.64
    Activations Density 0.035%

    No Known Activations