© 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. 956
    Prev
    Next
    INDEX
    Explanations

    military

    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
    WriteTagHelper
    -0.80
    HtmlAttribute
    -0.72
     endforeach
    -0.68
    SourceChecksum
    -0.65
     استنادى
    -0.63
    GEBURTSDATUM
    -0.61
    Население
    -0.60
    +:+
    -0.59
    EDEFAULT
    -0.59
    IndentedString
    -0.59
    POSITIVE LOGITS
    länger
    0.44
    velocityY
    0.43
     Anerkennung
    0.42
     PREMI
    0.40
    velocityX
    0.40
    fordern
    0.39
     rasanya
    0.39
     AV
    0.39
    visející
    0.39
     ASP
    0.39
    Activations Density 0.109%

    No Known Activations