© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96321
    Prev
    Next
    INDEX
    Explanations

    code

    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
     also
    -0.55
     quiera
    -0.54
    also
    -0.52
     dessutom
    -0.50
    ’
    -0.49
     Also
    -0.48
     säkert
    -0.48
     puisse
    -0.48
    opies
    -0.47
    '
    -0.47
    POSITIVE LOGITS
     exposing
    0.69
    RenderAtEndOf
    0.69
     dealing
    0.68
     having
    0.67
     repetitive
    0.66
     administering
    0.66
     reflecting
    0.66
     getting
    0.66
     focusing
    0.65
     allowing
    0.65
    Activations Density 0.001%

    No Known Activations