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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1498
    Prev
    Next
    INDEX
    Explanations

    mechanical or procedural processes

    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
    -0.91
     processing
    -0.90
     PROCESSING
    -0.80
    Processing
    -0.79
    processing
    -0.72
    rites
    -0.70
    rite
    -0.70
    __*/
    -0.65
    PROCESSING
    -0.64
     myſelf
    -0.64
    POSITIVE LOGITS
    ה
    0.61
    ंदीखरीदारी
    0.60
    i
    0.60
     <<<<<<<<<<<<<<
    0.55
     aDecoder
    0.54
     Gins
    0.48
    a
    0.47
     allAfrica
    0.46
    livejournal
    0.46
    <eos>
    0.45
    Activations Density 1.189%

    No Known Activations