© 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. 43300
    Prev
    Next
    INDEX
    Explanations

    adverbs of time/degree

    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
     cures
    -0.81
     rotations
    -0.80
     prescriptions
    -0.79
     choices
    -0.77
     solos
    -0.77
     itineraries
    -0.76
     postures
    -0.73
     stages
    -0.73
     touches
    -0.73
     citations
    -0.73
    POSITIVE LOGITS
     âmes
    0.69
     épaules
    0.64
     émissions
    0.63
     maux
    0.62
     phénomènes
    0.61
     vœux
    0.59
     modalités
    0.59
     doigts
    0.58
     oreilles
    0.57
     oiseaux
    0.57
    Activations Density 0.072%

    No Known Activations