© 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. 45583
    Prev
    Next
    INDEX
    Explanations

    pose or dehydration

    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
     Express
    -0.85
     express
    -0.83
     expressed
    -0.82
     pose
    -0.82
     expresses
    -0.78
     expressing
    -0.75
     De
    -0.74
    Express
    -0.66
    expressed
    -0.66
     de
    -0.64
    POSITIVE LOGITS
    +#+#
    0.73
     становника
    0.70
    ReusableCell
    0.68
     betweenstory
    0.65
    jší
    0.63
    AddTagHelper
    0.61
    الحياه
    0.60
     religieuses
    0.60
    ContextHolder
    0.60
    ChildScrollView
    0.60
    Activations Density 1.640%

    No Known Activations