© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94183
    Prev
    Next
    INDEX
    Explanations

    kyt

    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
     BoxDecoration
    -0.69
     ujednoznacz
    -0.62
     itſelf
    -0.61
     fevere
    -0.60
     unſ
    -0.59
     Majefty
    -0.59
     becauſe
    -0.57
     perſon
    -0.56
    ſelves
    -0.56
     myſelf
    -0.56
    POSITIVE LOGITS
    īt
    0.59
    ījum
    0.52
     Franklin
    0.52
     Rac
    0.51
    ActionResult
    0.49
    fin
    0.49
    vert
    0.48
     cref
    0.48
     cat
    0.47
    īj
    0.46
    Activations Density 0.030%

    No Known Activations