© 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. 1-CLT-HP
    7. 10044
    Prev
    Next
    INDEX
    Explanations

    Ju

    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
    GOTREF
    -0.61
    createCanvas
    -0.60
    ########.
    -0.57
    encodeWith
    -0.56
     structure
    -0.55
    specialchars
    -0.52
    QtCore
    -0.52
    الإنجليزية
    -0.51
     con
    -0.50
     nonatomic
    -0.50
    POSITIVE LOGITS
    FormTagHelper
    0.58
     mourut
    0.54
     preghi
    0.53
     auroit
    0.53
    /**
    0.52
     sentimenti
    0.52
     difficultés
    0.51
     fråga
    0.50
     avoient
    0.50
     veckor
    0.50
    Activations Density 0.015%

    No Known Activations