© 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. 14777
    Prev
    Next
    INDEX
    Explanations

    smart

    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
     InputDecoration
    -0.97
    WaitGroup
    -0.82
    StoryboardSegue
    -0.82
    الحياه
    -0.80
     الحره
    -0.79
    berdayakan
    -0.79
     onAnimation
    -0.77
     CreateTagHelper
    -0.75
    BufferException
    -0.75
    Personensuche
    -0.74
    POSITIVE LOGITS
     national
    0.39
    πουργ
    0.36
     Ehre
    0.36
     city
    0.36
     ente
    0.36
     meter
    0.36
     mij
    0.35
     interess
    0.34
     and
    0.34
     metri
    0.34
    Activations Density 0.012%

    No Known Activations