© 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. 0-CLT-HP
    7. 94742
    Prev
    Next
    INDEX
    Explanations

    mix

    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
     kasarigan
    -0.71
    WebVitals
    -0.66
     voies
    -0.65
    ագրություններ
    -0.64
     provisoire
    -0.63
    transQ
    -0.62
     américains
    -0.62
    quelize
    -0.62
     StringVar
    -0.62
     fédé
    -0.61
    POSITIVE LOGITS
    ್
    0.55
    ington
    0.52
    organ
    0.51
    ങ്
    0.51
     promotion
    0.50
     uch
    0.50
    newBuilder
    0.49
     make
    0.48
    thorne
    0.48
     onError
    0.48
    Activations Density 0.049%

    No Known Activations