© 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. 20-CLT-HP
    7. 72060
    Prev
    Next
    INDEX
    Explanations

    Surface

    np_max-act-logits · 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
    Izvori
    -0.57
    ramide
    -0.54
    xase
    -0.52
     poveznice
    -0.51
    Oneof
    -0.51
    Tembelea
    -0.47
     pierre
    -0.47
    insee
    -0.47
     Sari
    -0.47
    johns
    -0.46
    POSITIVE LOGITS
     Surface
    0.72
    KommentareTeilen
    0.68
     Surfaces
    0.64
    InSection
    0.63
    Surface
    0.63
     net
    0.63
     ContentValues
    0.62
     Spectre
    0.62
    IsContent
    0.61
     Retina
    0.59
    Activations Density 0.005%

    No Known Activations