© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5665
    Prev
    Next
    INDEX
    Explanations

    typefaces and fonts

    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
     calendriers
    -0.58
    borderBottom
    -0.56
    ysteem
    -0.54
     cared
    -0.52
    رسد
    -0.51
     barbacoa
    -0.49
    ystem
    -0.48
     Tahu
    -0.48
     Borden
    -0.47
     Oats
    -0.47
    POSITIVE LOGITS
     فريبيس
    0.74
    tvguidetime
    0.65
     defaultstate
    0.65
     GlobalKey
    0.64
    AndroidJUnit
    0.64
    CloseOperation
    0.58
    الإنجليزية
    0.56
    URLException
    0.55
    بوابة
    0.54
     дописавши
    0.54
    Activations Density 0.001%

    No Known Activations