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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1453
    Prev
    Next
    INDEX
    Explanations

    descriptions of houses and real estate, particularly features and rooms.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     hostels
    -0.92
     hotels
    -0.86
    Hotels
    -0.84
     Hotels
    -0.81
     hôtels
    -0.81
     Hotel
    -0.78
     hotel
    -0.78
    Hotel
    -0.75
     hostel
    -0.74
    hotels
    -0.72
    POSITIVE LOGITS
     LARGE
    0.66
     large
    0.66
     Winaray
    0.66
     HUGE
    0.63
     Large
    0.59
     Huge
    0.58
     huge
    0.57
     double
    0.57
     spacious
    0.56
     oversized
    0.56
    Activations Density 0.170%

    No Known Activations