© 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. 15473
    Prev
    Next
    INDEX
    Explanations

    references to the location of a specific apartment or building

    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
     residence
    -1.41
    Residential
    -1.32
     residential
    -1.31
     Residence
    -1.29
     Residential
    -1.28
    residential
    -1.20
    residence
    -1.17
    Residence
    -1.16
     residences
    -1.13
     RESIDENCE
    -1.09
    POSITIVE LOGITS
     apartment
    1.40
    apartment
    1.16
     Apartment
    1.02
    Apartment
    0.97
     apartments
    0.74
     apartamento
    0.73
     APART
    0.64
     appartement
    0.61
    maris
    0.60
    appartement
    0.60
    Activations Density 0.006%

    No Known Activations