© 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. 720
    Prev
    Next
    INDEX
    Explanations

    time

    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
    NB
    -0.47
    gawai
    -0.41
     сча
    -0.40
    inh
    -0.38
    了一下
    -0.38
    álva
    -0.38
    生平
    -0.37
    dama
    -0.36
    bihi
    -0.36
     bot
    -0.36
    POSITIVE LOGITS
    StructEnd
    0.75
    amaño
    0.73
     viewDidLoad
    0.72
    viewDidLoad
    0.71
    RunAsync
    0.71
    RegistryLite
    0.70
    Tracce
    0.69
     Efq
    0.68
     auroit
    0.67
     étoit
    0.65
    Activations Density 0.014%

    No Known Activations