© 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. 13961
    Prev
    Next
    INDEX
    Explanations

    references to specific animal species, particularly rabbits

    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
     animal
    -0.94
     Animal
    -0.73
     mouse
    -0.72
     rat
    -0.68
    animal
    -0.66
     ANIMAL
    -0.66
     Mouse
    -0.65
    Animal
    -0.65
     Rat
    -0.57
    mouse
    -0.56
    POSITIVE LOGITS
     rabbits
    1.38
     monkeys
    1.32
     swans
    1.27
     chickens
    1.23
     ducks
    1.16
     pigs
    1.16
     turkeys
    1.15
     wolves
    1.14
     goats
    1.13
     cats
    1.12
    Activations Density 0.034%

    No Known Activations