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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13946
    Prev
    Next
    INDEX
    Explanations

    references to honey or honey-related products

    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
    bee
    -1.05
    Bee
    -0.92
     Bee
    -0.83
     initComponents
    -0.82
     ant
    -0.78
     FetchType
    -0.77
    BEE
    -0.76
    ToScroll
    -0.73
    bees
    -0.72
     Copper
    -0.72
    POSITIVE LOGITS
     honey
    2.75
    honey
    2.41
     Honey
    2.39
    Honey
    2.31
     HONEY
    2.08
     sweetie
    0.91
     honeymoon
    0.89
     madu
    0.89
     Honeymoon
    0.87
     Honig
    0.86
    Activations Density 0.001%

    No Known Activations