© 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. 0-CLT-HP
    4. 1289
    Prev
    Next
    INDEX
    Explanations

    subsidiary companies

    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
     streams
    -0.91
    lier
    -0.83
     Streams
    -0.82
    streams
    -0.77
    Streams
    -0.56
     CommandType
    -0.54
    heimer
    -0.51
     betweenstory
    -0.50
    graduate
    -0.48
    écnicas
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.80
     الحره
    0.74
    InSection
    0.74
     InputDecoration
    0.72
    Hentet
    0.68
     propOrder
    0.66
    ModelForm
    0.63
     BoxFit
    0.59
    NameInMap
    0.59
    openqa
    0.58
    Activations Density 0.038%

    No Known Activations