© 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. 0-CLT-HP
    7. 40404
    Prev
    Next
    INDEX
    Explanations

    scoring

    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
     resourceCulture
    -0.86
     istället
    -0.85
     addition
    -0.85
     Addition
    -0.84
     Efq
    -0.83
    Референце
    -0.82
     Counting
    -0.82
     instead
    -0.81
     Majefty
    -0.79
    ponses
    -0.77
    POSITIVE LOGITS
     Egypt
    0.48
     to
    0.46
     its
    0.44
     patron
    0.43
     Christians
    0.42
     Muslims
    0.42
     of
    0.42
     minister
    0.42
     Israel
    0.41
     Nigeria
    0.41
    Activations Density 0.028%

    No Known Activations