© 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. 5-CLT-HP
    7. 3390
    Prev
    Next
    INDEX
    Explanations

    sitting, furniture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sitting
    -0.83
     sitting
    -0.80
     seating
    -0.79
     seat
    -0.79
     sit
    -0.77
     sits
    -0.77
     Sit
    -0.74
     Seating
    -0.73
     Seat
    -0.73
     chair
    -0.71
    POSITIVE LOGITS
    Lähteet
    0.68
     &___
    0.60
     próprias
    0.57
     prossimo
    0.55
     negozio
    0.54
     intervento
    0.54
     alimentazione
    0.53
     falando
    0.52
     tecniche
    0.51
     aisladas
    0.51
    Activations Density 0.001%

    No Known Activations