© 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. 46027
    Prev
    Next
    INDEX
    Explanations

    software 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
     attacker
    -0.94
     attackers
    -0.84
    findpost
    -0.83
    sizeCache
    -0.66
     attacking
    -0.60
    setVerticalGroup
    -0.59
     attack
    -0.58
    attacker
    -0.56
     kasarigan
    -0.56
     attacked
    -0.55
    POSITIVE LOGITS
    migrationBuilder
    0.69
     Efq
    0.68
     bower
    0.59
     photolibrary
    0.57
     Huguen
    0.57
     Económica
    0.56
     SEK
    0.56
     Spaghetti
    0.56
     doubtnut
    0.56
     Belg
    0.55
    Activations Density 0.029%

    No Known Activations