© 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. 1-RES-MATRYOSHKA-DC
    7. 691
    Prev
    Next
    INDEX
    Explanations

    references to the character Daisuke using various forms of the name and related terms

    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
     Butterfield
    -0.90
    łgorzata
    -0.82
    ibatis
    -0.72
     Kirkpatrick
    -0.72
     Efq
    -0.71
    Autowired
    -0.70
    ggak
    -0.69
    riguez
    -0.66
     marito
    -0.65
     fiore
    -0.65
    POSITIVE LOGITS
    fen
    1.48
    hen
    1.46
    zen
    1.45
     CEN
    1.44
     SEN
    1.40
    ken
    1.38
     den
    1.38
    ben
    1.37
    pen
    1.36
    sen
    1.36
    Activations Density 2.017%

    No Known Activations