© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1917
    Prev
    Next
    INDEX
    Explanations

    tilt

    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
    DockStyle
    -1.13
    TagMode
    -1.13
     <=",
    -1.09
     bezeichneter
    -1.07
    setVerticalGroup
    -1.05
     تضيفلها
    -1.04
    LookAnd
    -1.03
    IUrlHelper
    -0.99
    RectangleBorder
    -0.98
    Personendaten
    -0.98
    POSITIVE LOGITS
     of
    0.69
    als
    0.65
     S
    0.60
     g
    0.59
     G
    0.59
     in
    0.57
     E
    0.57
     (
    0.57
     
    0.56
     he
    0.55
    Activations Density 0.123%

    No Known Activations