© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92384
    Prev
    Next
    INDEX
    Explanations

    goggles

    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
     receptors
    -0.73
     movements
    -0.69
     labs
    -0.67
    IndentedString
    -0.66
     precautions
    -0.60
     Precautions
    -0.60
     laboratories
    -0.56
    movements
    -0.56
    roides
    -0.55
     foundations
    -0.54
    POSITIVE LOGITS
    hips
    0.69
    ness
    0.65
    httphttps
    0.58
    енча
    0.57
    ynthesis
    0.57
     correctes
    0.57
    SourceChecksum
    0.54
     CreateTagHelper
    0.54
    期刊论文
    0.54
     translating
    0.52
    Activations Density 1.584%

    No Known Activations