© 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. 93294
    Prev
    Next
    INDEX
    Explanations

    large numbers

    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
     countless
    -0.82
     dozens
    -0.74
     dozen
    -0.73
     overwhelming
    -0.72
     crore
    -0.68
     innumerable
    -0.68
     Millions
    -0.68
     centaines
    -0.67
     milliers
    -0.66
     Millionen
    -0.66
    POSITIVE LOGITS
    ing
    0.56
    Tracce
    0.55
    withstanding
    0.52
    nloa
    0.49
    ising
    0.48
    ###
    0.46
    src
    0.45
    enter
    0.45
    ning
    0.45
    ingly
    0.45
    Activations Density 0.166%

    No Known Activations