© 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. 18-RES-MATRYOSHKA-DC
    7. 262
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and words related to buildings

    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.18.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.18.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
    tvguidetime
    -0.86
    AndEndTag
    -0.77
     nahilalakip
    -0.75
     виправивши
    -0.75
    PickerController
    -0.73
    protoimpl
    -0.69
     AssemblyCulture
    -0.68
    رشف
    -0.68
     ddelweddau
    -0.68
     الحره
    -0.66
    POSITIVE LOGITS
     buildings
    1.20
     renovated
    1.16
     building
    1.12
     adjacent
    1.09
     facilities
    1.07
     spacious
    1.07
     built
    1.04
     adjoining
    1.03
     amenities
    1.02
     renovations
    0.98
    Activations Density 2.933%

    No Known Activations