© 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. 10288
    Prev
    Next
    INDEX
    Explanations

    happen

    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
     sauvages
    -0.93
     ſtate
    -0.89
     Monfieur
    -0.80
     küche
    -0.79
     Jefus
    -0.78
     zelve
    -0.78
     anhänger
    -0.77
     avoient
    -0.77
     chré
    -0.76
     themſelves
    -0.75
    POSITIVE LOGITS
    ,
    0.59
     “
    0.57
     sp
    0.53
    .
    0.50
    /
    0.49
     n
    0.48
    pmatrix
    0.48
    ?”
    0.48
     onPostExecute
    0.47
     rund
    0.46
    Activations Density 0.013%

    No Known Activations