© 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. 11427
    Prev
    Next
    INDEX
    Explanations

    weapons/firearms

    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
    RenderAtEndOf
    -0.70
    KindOfClass
    -0.68
    actéristi
    -0.67
    +#+
    -0.65
    ientí
    -0.65
     CreateTagHelper
    -0.65
    tifical
    -0.64
    ennifer
    -0.63
    vironment
    -0.63
    eradish
    -0.63
    POSITIVE LOGITS
    MeasureSpec
    0.42
     possessed
    0.40
     administration
    0.39
     Answered
    0.39
    TProtocol
    0.38
     allowed
    0.38
     held
    0.38
    BeginInit
    0.37
    SpringBootTest
    0.37
     transferred
    0.37
    Activations Density 0.029%

    No Known Activations