© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 91964
    Prev
    Next
    INDEX
    Explanations

    oz

    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
    fied
    -0.54
     sik
    -0.51
    iy
    -0.49
    Give
    -0.48
    oi
    -0.47
    IY
    -0.47
     cooperation
    -0.46
     possibilités
    -0.46
    iw
    -0.46
     عمان
    -0.44
    POSITIVE LOGITS
    s
    0.81
     pinulongan
    0.71
    sendMail
    0.61
    UnusedPrivate
    0.60
     CreateTagHelper
    0.59
    aarrggbb
    0.59
    sine
    0.58
    følgelig
    0.58
    ьогодні
    0.57
    getSupport
    0.57
    Activations Density 0.349%

    No Known Activations