© 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. 40440
    Prev
    Next
    INDEX
    Explanations

    Data in rows and columns

    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
    -1.52
    ſelf
    -1.45
     myſelf
    -1.45
     Monfieur
    -1.40
     Majefty
    -1.38
     reaſon
    -1.37
     Anſ
    -1.36
     Jefus
    -1.34
     purpoſe
    -1.34
     Reſ
    -1.32
    POSITIVE LOGITS
    ,
    0.93
     and
    0.88
    .
    0.81
     of
    0.77
     (
    0.76
     in
    0.76
     for
    0.73
     from
    0.71
     
    0.71
     or
    0.70
    Activations Density 1.102%

    No Known Activations