© 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. 4-CLT-HP
    7. 400
    Prev
    Next
    INDEX
    Explanations

    of

    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
     genoux
    -0.65
     vaisseaux
    -0.65
     vœux
    -0.65
     tromper
    -0.62
     peines
    -0.60
     varandra
    -0.58
     déchir
    -0.57
     äldre
    -0.57
     vägen
    -0.56
     élevées
    -0.56
    POSITIVE LOGITS
     CreateTagHelper
    0.97
     possibilities
    0.75
     available
    0.74
    Vidite
    0.73
     possible
    0.73
     required
    0.69
     applicable
    0.68
     potential
    0.65
     ways
    0.65
     involved
    0.64
    Activations Density 0.003%

    No Known Activations