© 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. 1-CLT-HP
    7. 12482
    Prev
    Next
    INDEX
    Explanations

    W

    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
    ticle
    -0.59
    下
    -0.50
    Acro
    -0.45
    place
    -0.44
    i
    -0.44
    itive
    -0.43
    จุ
    -0.43
     Geräte
    -0.43
    iable
    -0.42
    acro
    -0.41
    POSITIVE LOGITS
    )։
    0.69
    GEBURTSDATUM
    0.68
     CreateTagHelper
    0.68
    HasForeignKey
    0.67
    ьаж
    0.67
    CharStream
    0.66
    setVerticalGroup
    0.66
    ArrowToggle
    0.62
    Filmografie
    0.59
     EClass
    0.59
    Activations Density 0.111%

    No Known Activations