© 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. 4-CLT-HP
    7. 1623
    Prev
    Next
    INDEX
    Explanations

    Website content

    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
    uxxxx
    -0.61
     intptr
    -0.59
     Мексичка
    -0.59
     ddelweddau
    -0.57
    BRUARY
    -0.57
    aktery
    -0.55
     चीज़ों
    -0.54
    beled
    -0.54
    uated
    -0.53
    quares
    -0.52
    POSITIVE LOGITS
    :
    0.73
     watching
    0.63
     listening
    0.61
    collectionView
    0.59
     visiting
    0.56
     taking
    0.56
     checking
    0.56
     viewing
    0.55
     looking
    0.54
     attending
    0.54
    Activations Density 0.018%

    No Known Activations