© 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. 45615
    Prev
    Next
    INDEX
    Explanations

    processing

    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
     processing
    -0.72
     Processing
    -0.67
    Processing
    -0.66
     PROCESSING
    -0.65
    processing
    -0.59
     processed
    -0.54
    XmlRootElement
    -0.50
    //
    -0.45
    Datuak
    -0.45
     Ego
    -0.45
    POSITIVE LOGITS
    はじめに
    0.52
    webElement
    0.52
    ̈́
    0.51
    তথ্যসূত্র
    0.51
    sizeCache
    0.50
    elett
    0.50
    цездатний
    0.50
    QPalette
    0.49
    IntentFilter
    0.49
     train
    0.49
    Activations Density 0.037%

    No Known Activations