Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14798
    Prev
    Next
    INDEX
    Explanations

    references to the "gard" or "gaard" term, which is associated with the concept of a fortified or defensive domain, often in the context of mythological or fantasy settings

    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
     wireType
    -0.58
     AssemblyTitle
    -0.46
    smoothing
    -0.44
    gel
    -0.43
     ale
    -0.43
     Puff
    -0.43
    </tbody>
    -0.42
     Ale
    -0.42
    ッサン
    -0.41
     Socialista
    -0.41
    POSITIVE LOGITS
    gard
    3.89
    gaard
    2.06
    GARD
    1.96
    Gard
    1.69
    gård
    1.68
     gard
    1.51
     Gard
    1.49
     GARD
    1.16
    garde
    1.12
    garder
    1.11
    Activations Density 0.001%

    No Known Activations