© 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. 96408
    Prev
    Next
    INDEX
    Explanations

    мы

    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
    ValueGeneration
    -0.63
    MemoryWarning
    -0.53
    alyptus
    -0.53
    navigationBar
    -0.48
    HasForeignKey
    -0.48
     formulario
    -0.47
    BagLayout
    -0.46
    хло
    -0.45
     dataSnapshot
    -0.44
    hassee
    -0.44
    POSITIVE LOGITS
     متعلقه
    0.66
    //});
    0.59
    //};
    0.56
     betweenstory
    0.56
    AutoScaleMode
    0.53
     dawned
    0.53
     and
    0.52
     content
    0.50
     '
    0.49
     worlds
    0.49
    Activations Density 0.000%

    No Known Activations