© 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. 45454
    Prev
    Next
    INDEX
    Explanations

    crime

    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
     Crime
    -1.14
    Crime
    -1.13
     crime
    -1.10
    crime
    -1.05
    DockStyle
    -1.05
     CRIME
    -1.04
     AssemblyCompany
    -1.02
    StoryboardSegue
    -0.95
     Crimes
    -0.91
    ,:),
    -0.88
    POSITIVE LOGITS
    z
    0.73
    io
    0.62
    m
    0.62
    rr
    0.61
    ine
    0.57
    str
    0.57
    net
    0.57
    x
    0.57
    or
    0.57
    ous
    0.57
    Activations Density 0.105%

    No Known Activations