© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11708
    Prev
    Next
    INDEX
    Explanations

    references to specific assignment-related words

    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
     allocated
    -1.13
    allocated
    -0.99
     allotted
    -0.89
     allocate
    -0.89
    TestingModule
    -0.88
    designated
    -0.88
     designated
    -0.87
     alloc
    -0.85
     assigned
    -0.85
     allocating
    -0.83
    POSITIVE LOGITS
     assignment
    2.36
     Assignment
    2.23
     assignments
    2.03
    Assignment
    1.95
     ASSIGNMENT
    1.86
     Assignments
    1.82
    assignment
    1.81
    Assignments
    1.41
    assignments
    1.36
     задания
    0.82
    Activations Density 0.003%

    No Known Activations