© 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. 15763
    Prev
    Next
    INDEX
    Explanations

    to

    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
    berdayakan
    -0.90
    ✨:
    -0.89
     Efq
    -0.84
     Majefty
    -0.82
     fevere
    -0.82
    antaranya
    -0.80
     sauvages
    -0.80
     AppColors
    -0.79
     parachoque
    -0.79
     poffible
    -0.79
    POSITIVE LOGITS
     form
    0.57
     let
    0.56
     help
    0.54
     hold
    0.45
    ga
    0.45
     stop
    0.44
     push
    0.44
    og
    0.44
    form
    0.44
     start
    0.44
    Activations Density 0.004%

    No Known Activations