© 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. 1-CLT-HP
    7. 14576
    Prev
    Next
    INDEX
    Explanations

    malware

    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
     malware
    -1.09
     Malware
    -1.05
    Malware
    -0.82
     وتسجيلات
    -0.64
     MainAxisSize
    -0.62
     StatefulWidget
    -0.59
    uries
    -0.56
    LLocation
    -0.55
    alism
    -0.54
    Abitanti
    -0.53
    POSITIVE LOGITS
     distribution
    0.52
    bytes
    0.48
     tarko
    0.46
     strains
    0.45
    byte
    0.44
    UnknownFields
    0.43
     Verteilung
    0.42
    InitStruct
    0.41
     generation
    0.41
    作者
    0.41
    Activations Density 0.053%

    No Known Activations