© 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. 4-CLT-HP
    7. 4662
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Roskov
    -0.70
    meaning
    -0.61
    Touching
    -0.60
    Meaning
    -0.59
    hésite
    -0.58
    وفاته
    -0.57
     समीक्षक
    -0.55
    AccessorTable
    -0.55
    PreferredItem
    -0.54
     nahilalakip
    -0.54
    POSITIVE LOGITS
     say
    0.61
     present
    0.58
     المعيارى
    0.55
     call
    0.46
    ╦
    0.45
     state
    0.45
     presente
    0.44
     show
    0.44
    原始内容存档
    0.43
    HEET
    0.43
    Activations Density 0.003%

    No Known Activations