© 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. 91943
    Prev
    Next
    INDEX
    Explanations

    atomic operations and mutexes

    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
    脚注の使い方
    -0.94
    withIdentifier
    -0.70
     متعلقه
    -0.70
    Geplaatst
    -0.66
    RTEX
    -0.65
    onActivityResult
    -0.65
    webElementXpaths
    -0.61
    الحياه
    -0.60
    ="@+
    -0.57
     ModelExpression
    -0.57
    POSITIVE LOGITS
    kuh
    0.40
    deli
    0.39
    Deleted
    0.39
     aikaa
    0.38
     Define
    0.38
    hr
    0.37
    getAs
    0.37
     HUGE
    0.36
    essége
    0.36
    具
    0.35
    Activations Density 0.005%

    No Known Activations