© 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. 1-CLT-HP
    7. 13066
    Prev
    Next
    INDEX
    Explanations

    \

    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
     StatelessWidget
    -0.63
     beginnetje
    -0.57
     defaultstate
    -0.57
     StatefulWidget
    -0.55
    errHandler
    -0.53
    WriteBarrier
    -0.52
     createState
    -0.49
    TagHelper
    -0.49
    rancy
    -0.49
     Bay
    -0.48
    POSITIVE LOGITS
    –>
    0.62
     ◦
    0.61
    ConstraintMaker
    0.56
     –>
    0.56
     <--
    0.55
    __(/*!
    0.55
     TPS
    0.55
     București
    0.54
    ](#
    0.52
     Mahomet
    0.52
    Activations Density 0.237%

    No Known Activations