© 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. 97252
    Prev
    Next
    INDEX
    Explanations

    Di

    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
    i
    -0.97
    s
    -0.93
    d
    -0.91
    t
    -0.88
    k
    -0.85
    n
    -0.84
    ly
    -0.83
    o
    -0.83
    p
    -0.83
    m
    -0.81
    POSITIVE LOGITS
     Majefty
    1.21
     myſelf
    1.20
     Jefus
    1.18
     Efq
    1.16
     itſelf
    1.16
     purpoſe
    1.15
     greateſt
    1.14
     themſelves
    1.12
     Monfieur
    1.12
     raiſ
    1.11
    Activations Density 0.052%

    No Known Activations