© 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. 92702
    Prev
    Next
    INDEX
    Explanations

    case

    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
     itſelf
    -0.79
     nahilalakip
    -0.74
     useRouter
    -0.72
     tilf
    -0.72
    AndEndTag
    -0.69
    ariate
    -0.69
     varandra
    -0.68
     חיצוניים
    -0.68
     Lordships
    -0.68
    utenant
    -0.67
    POSITIVE LOGITS
    y
    0.52
    onAttach
    0.51
     of
    0.50
    les
    0.46
     Numerade
    0.45
    ,
    0.43
    te
    0.42
     all
    0.42
    g
    0.42
     for
    0.41
    Activations Density 0.077%

    No Known Activations