© 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. 0-CLT-HP
    7. 95373
    Prev
    Next
    INDEX
    Explanations

    int

    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
     int
    -1.23
    int
    -0.87
     ad
    -0.64
    viewDidLoad
    -0.56
     Int
    -0.54
    BeginContext
    -0.54
     to
    -0.53
    ArrowToggle
    -0.49
    nonatomic
    -0.49
    setFlags
    -0.49
    POSITIVE LOGITS
     Wikiseite
    0.68
    ՚
    0.67
    OGND
    0.66
    enderror
    0.63
     يتيمه
    0.62
    #+#
    0.62
    protoimpl
    0.61
     CreateTagHelper
    0.60
     brancas
    0.58
    urium
    0.57
    Activations Density 1.607%

    No Known Activations