© 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. 4-CLT-HP
    7. 2055
    Prev
    Next
    INDEX
    Explanations

    "is" "are" verb to be

    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
     <=",
    -0.91
     chi̍t
    -0.68
    IndentedString
    -0.67
     ErrIntOverflow
    -0.65
    LookAnd
    -0.64
     trattano
    -0.60
    ngdoc
    -0.58
    RenderAtEndOf
    -0.57
    Sharper
    -0.56
    WriteTagHelper
    -0.55
    POSITIVE LOGITS
    StreamWriter
    0.50
    rita
    0.48
     ideal
    0.47
     loaded
    0.46
    шай
    0.45
    mêmes
    0.45
    iprot
    0.45
     password
    0.45
    PCell
    0.45
     freely
    0.43
    Activations Density 0.019%

    No Known Activations