© 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. 5-CLT-HP
    7. 97471
    Prev
    Next
    INDEX
    Explanations

    has long been

    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
     maintenance
    -0.41
     selalu
    -0.41
    昔から
    -0.40
    мір
    -0.39
     stanovnika
    -0.38
    zzazione
    -0.38
     stets
    -0.38
     bataille
    -0.38
     pulumi
    -0.38
    ètres
    -0.37
    POSITIVE LOGITS
     kasarigan
    0.87
    曖昧さ回避
    0.80
     استنادى
    0.77
    BeginInit
    0.74
     propOrder
    0.73
    +#+
    0.72
    ]^{-
    0.70
    setVerticalGroup
    0.70
    تقاوى
    0.69
     soon
    0.69
    Activations Density 0.006%

    No Known Activations