© 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-RES-MATRYOSHKA-DC
    7. 13513
    Prev
    Next
    INDEX
    Explanations

    references to tropical or tropical-related environments and phenomena

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    providedIn
    -0.73
     tro
    -0.68
    tro
    -0.66
    帖最后由
    -0.65
    Tro
    -0.64
     Tro
    -0.60
    Hentet
    -0.60
     aDecoder
    -0.58
    AutoField
    -0.57
    RetentionPolicy
    -0.57
    POSITIVE LOGITS
     tropical
    2.75
     Tropical
    2.42
    tropical
    2.31
    Tropical
    2.28
     tropics
    2.06
     tropicales
    1.64
     subtropical
    1.49
     TROP
    1.42
     tropic
    1.05
     rainforest
    0.78
    Activations Density 0.001%

    No Known Activations