© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41926
    Prev
    Next
    INDEX
    Explanations

    Recreation or the name Dean

    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
     recreation
    -2.17
     Recreation
    -1.55
    Recreation
    -1.52
     recre
    -1.34
     RECRE
    -1.27
     recreate
    -1.18
     Recre
    -1.16
     recreated
    -1.11
    Recre
    -1.05
     recreational
    -0.85
    POSITIVE LOGITS
    ally
    0.91
    als
    0.81
     noDo
    0.76
    ly
    0.75
    eting
    0.66
     فريبيس
    0.65
    alised
    0.64
    ︎
    0.64
    ary
    0.64
    alist
    0.64
    Activations Density 0.160%

    No Known Activations