© 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. 15751
    Prev
    Next
    INDEX
    Explanations

    hunt

    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
     Hunt
    -1.12
    Hunt
    -1.02
     hunt
    -0.97
    hunt
    -0.95
     HUNT
    -0.91
     hunting
    -0.78
     hunted
    -0.76
    Autowired
    -0.73
     Hunting
    -0.71
     hunters
    -0.70
    POSITIVE LOGITS
    ress
    0.69
     Normdatei
    0.58
    shark
    0.52
    schuh
    0.51
    resses
    0.49
     Paglinawan
    0.47
    sider
    0.47
    knot
    0.46
    setupUi
    0.46
    IntoConstraints
    0.45
    Activations Density 0.023%

    No Known Activations