© 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. 14618
    Prev
    Next
    INDEX
    Explanations

    scale or impact

    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
    ord
    -0.50
    ORD
    -0.48
     pran
    -0.48
    hatta
    -0.47
    titu
    -0.47
     Take
    -0.46
    ورد
    -0.45
    lapsingToolbar
    -0.44
    MESS
    -0.44
    prima
    -0.44
    POSITIVE LOGITS
     fédé
    0.66
     récomp
    0.66
     vastaan
    0.65
     remporté
    0.63
     termica
    0.62
     aveug
    0.62
     américains
    0.62
    withId
    0.61
     financières
    0.61
     chré
    0.60
    Activations Density 0.032%

    No Known Activations