© 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. 0-RES-MATRYOSHKA-DC
    7. 15649
    Prev
    Next
    INDEX
    Explanations

    references to boroughs or borough-related concepts

    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
    RetentionPolicy
    -0.71
    tonsoft
    -0.66
    GEBURTS
    -0.60
    clerosis
    -0.58
     Ooster
    -0.58
    IMPORTED
    -0.57
    Moist
    -0.57
    databind
    -0.56
    contentLoaded
    -0.55
     pretence
    -0.55
    POSITIVE LOGITS
     Borough
    3.58
     borough
    3.34
     boroughs
    2.33
    borough
    1.25
     Boro
    0.88
    AndEndTag
    0.65
    Brooklyn
    0.55
     sed
    0.51
     صوتيه
    0.51
    OUGH
    0.50
    Activations Density 0.001%

    No Known Activations