© 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
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 13542
    Prev
    Next
    INDEX
    Explanations

    references to a specific German village and related geographical or infrastructural features

    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
    americana
    -0.56
     للاسماء
    -0.55
     neceffary
    -0.54
     videre
    -0.52
     petitioners
    -0.52
     Phys
    -0.52
     PEC
    -0.52
     FetchType
    -0.52
    myspace
    -0.52
     mécan
    -0.50
    POSITIVE LOGITS
    dorff
    4.44
    dorf
    1.63
    dorfer
    0.87
     chi̍t
    0.64
    ">//
    0.61
    MigrationBuilder
    0.58
    HasBeenSet
    0.57
    diğimiz
    0.56
    ništvo
    0.56
    VYMaps
    0.55
    Activations Density 0.007%

    No Known Activations