© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4710
    Prev
    Next
    INDEX
    Explanations

    references to documents or items being incorporated or cited

    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
     Elvira
    -0.58
    GetMapping
    -0.57
     ECOLOG
    -0.57
    dista
    -0.56
    شت
    -0.54
    おり
    -0.54
    СТЬ
    -0.54
    jestel
    -0.54
    yste
    -0.53
     Cull
    -0.53
    POSITIVE LOGITS
     incorporated
    2.45
     incorporation
    2.38
     Incorporation
    2.28
     incorporate
    2.25
    corporated
    2.17
     Incorpor
    2.16
     INCORPOR
    2.11
     incorporating
    2.06
     incorporates
    1.99
    incorpor
    1.95
    Activations Density 0.012%

    No Known Activations