© 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. 15025
    Prev
    Next
    INDEX
    Explanations

    pejorative or mocking references to unflattering office behaviors or personalities

    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
    Vice
    -0.53
    ору
    -0.49
    çu
    -0.48
    Ple
    -0.48
     Vice
    -0.47
     oprot
    -0.44
    iprot
    -0.44
    inescence
    -0.43
     \,\
    -0.43
     stab
    -0.42
    POSITIVE LOGITS
     boss
    3.11
    boss
    2.66
     Boss
    2.66
    Boss
    2.56
     bosses
    2.38
     BOSS
    2.09
    BOSS
    1.77
    ボス
    1.13
     chefe
    1.13
     jefe
    1.10
    Activations Density 0.002%

    No Known Activations