© 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. 5-CLT-HP
    7. 605
    Prev
    Next
    INDEX
    Explanations

    materials, projects

    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
     متعلقه
    -0.47
    chomp
    -0.43
    φό
    -0.42
    Format
    -0.42
    belongsTo
    -0.40
    uyu
    -0.40
     immediate
    -0.40
    uri
    -0.40
    стро
    -0.40
     voltage
    -0.39
    POSITIVE LOGITS
    yntaxException
    0.81
    SourceChecksum
    0.78
     Baillargeon
    0.78
     كومونز
    0.71
    RegistryLite
    0.70
     nahilalakip
    0.65
    paksa
    0.64
     kaarangay
    0.63
     viewDidLoad
    0.63
    INCREF
    0.63
    Activations Density 0.000%

    No Known Activations