© 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. 5-CLT-HP
    7. 5749
    Prev
    Next
    INDEX
    Explanations

    solic

    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
     extracellular
    -0.57
    baric
    -0.54
     puissiez
    -0.54
     escuela
    -0.53
    ConfigureAwait
    -0.51
     blessés
    -0.50
     militaires
    -0.50
     fondament
    -0.49
     tecnici
    -0.49
     dipendenti
    -0.49
    POSITIVE LOGITS
    awtextra
    0.80
    TestingModule
    0.73
    +#+
    0.66
    ριο
    0.53
     оригіналу
    0.52
     leaflet
    0.51
     arşivlendi
    0.50
     שוליים
    0.50
    [++
    0.50
    LayoutConstraint
    0.50
    Activations Density 0.017%

    No Known Activations