© 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. 40179
    Prev
    Next
    INDEX
    Explanations

    chernobyl

    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
     Monfieur
    -1.45
     myſelf
    -1.39
     avoient
    -1.31
     itſelf
    -1.29
     ſeveral
    -1.26
     Efq
    -1.26
     Anſ
    -1.24
     raiſ
    -1.23
     auroit
    -1.22
     Diſ
    -1.20
    POSITIVE LOGITS
    s
    0.91
    ly
    0.86
    d
    0.82
    n
    0.79
    y
    0.75
    l
    0.72
    t
    0.69
    g
    0.68
    r
    0.68
    ers
    0.65
    Activations Density 1.528%

    No Known Activations