© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2869
    Prev
    Next
    INDEX
    Explanations

    Asia

    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
    первых
    -0.60
     and
    -0.50
    enumi
    -0.48
    sbereich
    -0.47
     derni
    -0.45
    quid
    -0.43
    Glob
    -0.43
    satunya
    -0.42
    ípio
    -0.40
    QUID
    -0.40
    POSITIVE LOGITS
    sizeCache
    0.90
     pleaſure
    0.78
    oredCriteria
    0.71
     мәкал
    0.69
     purpoſe
    0.69
     Efq
    0.68
     chert
    0.68
     виправивши
    0.68
     Poincaré
    0.67
     preſent
    0.67
    Activations Density 0.001%

    No Known Activations