© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15482
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or buildings

    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
     centres
    -1.30
     centre
    -1.22
    centre
    -1.07
     centers
    -0.78
    CodeAnalysis
    -0.77
     Económica
    -0.73
     Vapour
    -0.68
     favourably
    -0.68
     neighbourhood
    -0.67
     center
    -0.65
    POSITIVE LOGITS
     Center
    1.65
    Center
    0.99
     Ctr
    0.85
     CENTER
    0.82
     ligiloj
    0.69
     Centre
    0.60
    oredCriteria
    0.56
    UnusedPrivate
    0.54
     Administrativna
    0.54
     فريبيس
    0.53
    Activations Density 0.006%

    No Known Activations