© 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. 0-CLT-HP
    7. 93066
    Prev
    Next
    INDEX
    Explanations

    LCD screens and homeland security

    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
    rints
    -0.64
    rint
    -0.58
    ist
    -0.50
    im
    -0.48
    iz
    -0.46
    FileInput
    -0.46
    oc
    -0.45
     reac
    -0.45
    ad
    -0.45
    u
    -0.44
    POSITIVE LOGITS
     تضيفلها
    0.74
    CppMethod
    0.72
    sizeCache
    0.71
     nakalista
    0.69
    ьаж
    0.68
    AddTagHelper
    0.68
    abestanden
    0.65
    ChildScrollView
    0.65
    BibitemShut
    0.64
    談社
    0.64
    Activations Density 0.449%

    No Known Activations