© 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. 97145
    Prev
    Next
    INDEX
    Explanations

    processes and states

    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
     Levels
    -0.91
    Levels
    -0.77
    idle
    -0.70
     idle
    -0.69
    levels
    -0.62
     repose
    -0.61
     peaking
    -0.61
    IDLE
    -0.60
    azin
    -0.60
    undra
    -0.60
    POSITIVE LOGITS
    aarrggbb
    0.76
    
    0.70
    TagMode
    0.69
     CreateTagHelper
    0.60
     дописавши
    0.59
    EndProject
    0.58
    PullParser
    0.57
    politico
    0.57
     nahilalakip
    0.57
    SharedCtor
    0.55
    Activations Density 1.579%

    No Known Activations