© 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. 1-CLT-HP
    7. 10859
    Prev
    Next
    INDEX
    Explanations

    throw

    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
    otide
    -1.70
    +#+
    -0.56
    ίο
    -0.55
    はじめに
    -0.54
     useAppContext
    -0.53
     ostavi
    -0.53
    tomos
    -0.53
     Mlle
    -0.51
     dealloc
    -0.51
     Unesco
    -0.51
    POSITIVE LOGITS
    elemField
    0.58
     فريبيس
    0.52
    chir
    0.52
    veret
    0.50
     Becher
    0.48
     iscri
    0.47
    QMetaType
    0.47
    Syl
    0.46
    icago
    0.46
     oreille
    0.45
    Activations Density 0.003%

    No Known Activations