© 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. 1-CLT-HP
    7. 12444
    Prev
    Next
    INDEX
    Explanations

    aircraft

    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
     aircraft
    -0.65
    Machine
    -0.64
     Machine
    -0.63
    клопе
    -0.61
    Datuak
    -0.61
     Airplane
    -0.60
     airplane
    -0.60
     airc
    -0.60
     machine
    -0.60
     aeron
    -0.59
    POSITIVE LOGITS
     للاسماء
    0.54
    Skocz
    0.50
    Kapcsolódó
    0.49
    AddHtmlAttribute
    0.48
     iconTwitter
    0.47
    liac
    0.47
    photobucket
    0.47
    각주
    0.47
     Acesso
    0.46
    gdx
    0.45
    Activations Density 0.012%

    No Known Activations