© 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. 0-CLT-HP
    7. 1784
    Prev
    Next
    INDEX
    Explanations

    instance

    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
     instances
    -1.48
     instance
    -1.43
    instance
    -1.25
     Instances
    -1.20
     Instance
    -1.10
     wonder
    -1.09
    instances
    -1.07
    Instance
    -1.02
    Instances
    -0.93
     INSTANCE
    -0.91
    POSITIVE LOGITS
    存于互联网档案馆
    0.63
     of
    0.63
    simpleType
    0.61
     kasarigan
    0.59
    adaptiveStyles
    0.58
    able
    0.56
    lectro
    0.56
    WriteBarrier
    0.56
    帖最后由
    0.56
    ISupport
    0.54
    Activations Density 0.044%

    No Known Activations