© 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. 5-CLT-HP
    7. 3887
    Prev
    Next
    INDEX
    Explanations

    teenagers

    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
     Ecke
    -0.39
     *>
    -0.38
    Müller
    -0.35
     varandra
    -0.34
     otomatig
    -0.34
     mümkün
    -0.33
    csname
    -0.33
    achieved
    -0.32
     vårt
    -0.31
    }{{\
    -0.31
    POSITIVE LOGITS
    SourceChecksum
    0.79
     Roskov
    0.75
    TagMode
    0.75
    y
    0.71
    UserScript
    0.70
    はじめに
    0.70
    fjspx
    0.68
    basicConfig
    0.67
     CreateTagHelper
    0.67
     الحره
    0.66
    Activations Density 0.001%

    No Known Activations