© 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. 2580
    Prev
    Next
    INDEX
    Explanations

    android

    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
    LookAnd
    -1.13
    Personendaten
    -0.85
     pinulongan
    -0.81
    tanleria
    -0.79
    TagHelper
    -0.78
     Paglinawan
    -0.77
     Италијани
    -0.76
    MethodManager
    -0.75
    Personensuche
    -0.73
     يتيمه
    -0.72
    POSITIVE LOGITS
     to
    0.55
     for
    0.49
     not
    0.48
     both
    0.45
    both
    0.44
     confronti
    0.43
    BOTH
    0.42
     publiques
    0.41
     zowel
    0.39
     skydd
    0.39
    Activations Density 0.002%

    No Known Activations