© 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. 6223
    Prev
    Next
    INDEX
    Explanations

    references to specific artworks and their presentation details

    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
     Wikispecies
    -0.67
     ἐκ
    -0.51
     Verenig
    -0.51
     néglig
    -0.51
     behoort
    -0.50
    Jeografia
    -0.50
    μία
    -0.48
    bahaya
    -0.46
    hib
    -0.46
     lazo
    -0.45
    POSITIVE LOGITS
    ment
    3.47
    ments
    3.16
    MENT
    2.98
    MENTS
    2.44
    EMENT
    2.13
     ment
    1.95
    ement
    1.95
    mento
    1.84
    Ment
    1.83
    menta
    1.77
    Activations Density 0.026%

    No Known Activations