© 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. 1-CLT-HP
    7. 9841
    Prev
    Next
    INDEX
    Explanations

    prices costs

    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
     E
    -0.54
    ар
    -0.52
    il
    -0.52
     Am
    -0.50
     T
    -0.50
    n
    -0.49
    p
    -0.49
     W
    -0.47
     P
    -0.47
    co
    -0.46
    POSITIVE LOGITS
     betweenstory
    1.06
     ComVisible
    0.84
    WriteTagHelper
    0.80
     الدولى
    0.77
    Билгалдахарш
    0.76
     Autorizaciones
    0.73
     bezeichneter
    0.73
     itſelf
    0.73
     otomatig
    0.71
     surla
    0.71
    Activations Density 0.185%

    No Known Activations