© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 154
    Prev
    Next
    INDEX
    Explanations

    terms related to educational facilities and community amenities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     trans
    -0.36
     Filho
    -0.36
     Brésil
    -0.35
     analysis
    -0.35
     valutazione
    -0.35
     Suiza
    -0.34
     świecie
    -0.34
     indeks
    -0.34
    wanderung
    -0.33
     I
    -0.33
    POSITIVE LOGITS
     rooms
    0.97
     buildings
    0.92
     houses
    0.90
     renovated
    0.90
     spacious
    0.87
     apartments
    0.86
     Rooms
    0.86
     floors
    0.85
     penthouse
    0.85
     roof
    0.85
    Activations Density 2.753%

    No Known Activations