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. 74386
    Prev
    Next
    INDEX
    Explanations

    Android code

    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
     kasarigan
    -0.77
     InputDecoration
    -0.74
     jScrollPane
    -0.70
     {}));
    -0.68
    зулта
    -0.63
    erializer
    -0.62
     intptr
    -0.61
    ChildIndex
    -0.61
    IBOutlet
    -0.60
    ustes
    -0.60
    POSITIVE LOGITS
    OGND
    0.42
     '\\;'
    0.42
    oll
    0.42
    ity
    0.42
     thuật
    0.40
     Towel
    0.40
     escur
    0.39
     Ral
    0.39
     QUAL
    0.38
     patatas
    0.37
    Activations Density 0.017%

    No Known Activations