© 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. 12-RES-MATRYOSHKA-DC
    7. 5473
    Prev
    Next
    INDEX
    Explanations

    references to houses and related entities in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wilfred
    -0.90
     Avid
    -0.87
     belf
    -0.84
     Mercan
    -0.83
    ergies
    -0.82
     Raptors
    -0.81
     canary
    -0.80
     Didi
    -0.78
     bershka
    -0.77
     LDAP
    -0.77
    POSITIVE LOGITS
     houses
    1.41
     House
    1.39
     Houses
    1.37
    Houses
    1.37
     house
    1.35
    House
    1.28
    houses
    1.21
     HOUSE
    1.20
    HOUSE
    1.19
    house
    1.18
    Activations Density 0.068%

    No Known Activations