© 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. 20-CLT-HP
    4. 74882
    Prev
    Next
    INDEX
    Explanations

    nose

    np_max-act-logits · 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
     nahilalakip
    -0.71
    帖最后由
    -0.70
     صوتيه
    -0.67
    complexType
    -0.66
    tagHelperRunner
    -0.65
     Axe
    -0.64
    InvalidProtocol
    -0.62
    RegressionTest
    -0.60
    WebVitals
    -0.60
     autorytatywna
    -0.60
    POSITIVE LOGITS
    StoryboardSegue
    0.50
     faldas
    0.43
     root
    0.43
    biol
    0.41
    ble
    0.41
    ilarang
    0.39
    pe
    0.38
    pir
    0.38
    KommentareTeilen
    0.37
     origem
    0.37
    Activations Density 0.001%

    No Known Activations