© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 93478
    Prev
    Next
    INDEX
    Explanations

    it

    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
     pinulongan
    -0.71
     către
    -0.64
    y
    -0.63
     Paglinawan
    -0.61
    ingly
    -0.61
     digne
    -0.60
     aastal
    -0.58
     superiori
    -0.58
     navideño
    -0.57
    to
    -0.57
    POSITIVE LOGITS
     are
    1.07
     can
    1.03
     will
    0.88
     may
    0.82
     must
    0.81
     would
    0.78
     might
    0.77
     do
    0.76
     cannot
    0.75
     could
    0.72
    Activations Density 0.114%

    No Known Activations