© 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. 4-CLT-HP
    7. 859
    Prev
    Next
    INDEX
    Explanations

    caravan

    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
     تضيفلها
    -0.84
    AddTagHelper
    -0.54
    */}
    -0.54
    DockStyle
    -0.54
    ("")]
    -0.54
    InjectAttribute
    -0.52
     invokingState
    -0.52
    ViewFeatures
    -0.52
    ToBounds
    -0.51
    SharedCtor
    -0.51
    POSITIVE LOGITS
    président
    0.57
    SizeMode
    0.56
     Vergara
    0.51
    исленность
    0.50
    eqref
    0.48
    maschinen
    0.47
     Cres
    0.47
     invade
    0.46
    po
    0.46
     of
    0.46
    Activations Density 0.003%

    No Known Activations