© 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. 0-CLT-HP
    7. 92307
    Prev
    Next
    INDEX
    Explanations

    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
    security
    -1.42
    ChildScrollView
    -0.74
    saraba
    -0.71
    SharedCtor
    -0.71
    NOPQRST
    -0.65
    脚注の使い方
    -0.65
     JpaRepository
    -0.65
    Personensuche
    -0.64
     InputDecoration
    -0.64
    PerformLayout
    -0.63
    POSITIVE LOGITS
    Personendaten
    0.59
    ized
    0.54
    BeginContext
    0.52
    dă
    0.52
    eace
    0.52
    ódio
    0.52
    dır
    0.51
    !("{}",
    0.49
    lardır
    0.49
     CHtml
    0.49
    Activations Density 0.974%

    No Known Activations