© 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. 94796
    Prev
    Next
    INDEX
    Explanations

    code/data

    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
    BeginContext
    -0.85
    LookAnd
    -0.79
    WillAppear
    -0.76
     '\\;'
    -0.75
    featureID
    -0.70
    AndEndTag
    -0.69
     ویکی‌آمباردا
    -0.68
    UVWXYZ
    -0.68
    InstrumentedTest
    -0.66
    rawDesc
    -0.65
    POSITIVE LOGITS
     and
    0.49
     rayures
    0.40
    A
    0.40
    gun
    0.39
     &
    0.38
    attendre
    0.38
    W
    0.38
     And
    0.38
    H
    0.38
    B
    0.38
    Activations Density 0.001%

    No Known Activations