© 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. 1-CLT-HP
    7. 11989
    Prev
    Next
    INDEX
    Explanations

    explosives/weaponry

    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
     bombs
    -1.17
     Bombs
    -0.81
    bombs
    -0.71
     nakalista
    -0.61
    assignment
    -0.43
     addition
    -0.43
     accomplishment
    -0.41
     adoption
    -0.41
     combat
    -0.40
     option
    -0.40
    POSITIVE LOGITS
     ThemeData
    0.78
    cshtml
    0.77
    BeginInit
    0.73
    WebControls
    0.71
    DockStyle
    0.71
     كومونز
    0.69
    BufferException
    0.68
    AddHtmlAttribute
    0.68
    StreetMap
    0.66
     AssemblyTitle
    0.65
    Activations Density 0.007%

    No Known Activations