© 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-CLT-HP
    7. 9299
    Prev
    Next
    INDEX
    Explanations

    image

    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
     المعيارى
    -0.76
     betweenstory
    -0.72
    Tē
    -0.65
    itarian
    -0.63
     faveur
    -0.63
     createSprite
    -0.63
    ècie
    -0.62
    itattu
    -0.62
     '../../../../
    -0.61
    цездатний
    -0.60
    POSITIVE LOGITS
     signal
    0.60
     intensification
    0.59
     pattern
    0.50
     sensor
    0.49
     circle
    0.47
     plate
    0.46
     projector
    0.46
    signal
    0.45
     presentation
    0.45
    InstanceState
    0.44
    Activations Density 0.084%

    No Known Activations