Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74475
    Prev
    Next
    INDEX
    Explanations

    violence

    np_max-act-logits · 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
     douce
    -0.60
    principalTable
    -0.58
    omock
    -0.57
     driven
    -0.57
     pinulongan
    -0.56
    Personendaten
    -0.55
     Irishman
    -0.54
     незавершена
    -0.54
    Datuak
    -0.54
    ardan
    -0.54
    POSITIVE LOGITS
     Audiodateien
    0.58
     NSCoder
    0.50
     initComponents
    0.48
    uxxxx
    0.48
    曖昧さ回避
    0.43
    ByExample
    0.40
     disambiguazione
    0.40
     Ons
    0.39
    supra
    0.39
     IndexPath
    0.39
    Activations Density 0.002%

    No Known Activations