© 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. 90865
    Prev
    Next
    INDEX
    Explanations

    ly

    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
     Su
    -0.68
    LY
    -0.65
     ly
    -0.63
     U
    -0.60
     
    -0.58
     LY
    -0.57
     #
    -0.57
     or
    -0.57
     (
    -0.56
     Scha
    -0.56
    POSITIVE LOGITS
     itſelf
    1.49
     myſelf
    1.47
     Reſ
    1.38
     Efq
    1.38
     Monfieur
    1.34
     themſelves
    1.33
     Majefty
    1.31
     Anſ
    1.30
     raiſ
    1.27
     purpoſe
    1.26
    Activations Density 0.244%

    No Known Activations