© 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. 4946
    Prev
    Next
    INDEX
    Explanations

    references to specific instruction-related data entries

    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
     urbanas
    -0.73
     وتسجيلات
    -0.70
    ⎨
    -0.68
    ########.
    -0.67
     EconPapers
    -0.65
    pośred
    -0.64
    ITECH
    -0.64
     "..\..\
    -0.62
    ="<?=$
    -0.61
     cykel
    -0.60
    POSITIVE LOGITS
    inst
    3.64
    Inst
    3.30
     inst
    3.00
     Inst
    2.97
    INST
    2.72
     INST
    2.52
     insta
    1.59
    insta
    1.36
     Insta
    1.34
    Insta
    1.33
    Activations Density 0.020%

    No Known Activations