© 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. 5-CLT-HP
    4. 3009
    Prev
    Next
    INDEX
    Explanations

    1

    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
    enderror
    -0.68
    <bos>
    -0.62
    \{\\
    -0.61
    存于互联网档案馆
    -0.52
     nahilalakip
    -0.51
    XmlEnum
    -0.51
    )"),
    -0.50
    \]
    -0.50
     المعيارى
    -0.50
    UserScript
    -0.49
    POSITIVE LOGITS
    0
    0.72
     <>",
    0.53
    BIDDEN
    0.52
     Dha
    0.49
     stages
    0.48
     CountDown
    0.47
    2
    0.46
    assar
    0.45
    صالات
    0.45
    oray
    0.45
    Activations Density 0.047%

    No Known Activations