© 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. 2-RES-MATRYOSHKA-DC
    7. 3673
    Prev
    Next
    INDEX
    Explanations

    modern and historical information about sports figures and their careers

    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
    новништво
    -0.57
    li
    -0.54
    öl
    -0.51
     workers
    -0.49
     employees
    -0.49
    chw
    -0.49
     Sepp
    -0.49
    ORUM
    -0.49
     employee
    -0.49
    inkov
    -0.49
    POSITIVE LOGITS
     career
    3.08
    career
    2.83
    Career
    2.75
     Career
    2.72
     CAREER
    2.56
     careers
    2.42
    CAREER
    2.33
     carrière
    2.03
     Karriere
    1.97
     Careers
    1.95
    Activations Density 0.006%

    No Known Activations