© 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. 92144
    Prev
    Next
    INDEX
    Explanations

    auxiliary verb "be"/"do"/"have"

    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
    فحة
    -0.56
    ʖ
    -0.50
    onAttach
    -0.49
    higan
    -0.48
    ongoose
    -0.46
    руем
    -0.45
    broek
    -0.44
    VERTISING
    -0.44
    出版年
    -0.44
    uality
    -0.43
    POSITIVE LOGITS
     ostavi
    0.80
    setVerticalGroup
    0.72
    recently
    0.71
     Infórmanos
    0.71
    recent
    0.69
    Recently
    0.66
     recentemente
    0.66
     recenti
    0.66
    Recent
    0.66
    Previously
    0.65
    Activations Density 0.188%

    No Known Activations