© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 12535
    Prev
    Next
    INDEX
    Explanations

    descriptions related to lattice structures and their partitioning schemes

    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
     transférez
    -0.63
    PYX
    -0.63
    mergeFrom
    -0.63
    iencies
    -0.58
    SCRIBE
    -0.56
     })}
    -0.56
     Humans
    -0.55
    writeField
    -0.54
     EDF
    -0.54
     gott
    -0.53
    POSITIVE LOGITS
    IntoConstraints
    0.82
    TagMode
    0.74
    rungsseite
    0.70
    enterOuterAlt
    0.67
     informée
    0.59
     Counselling
    0.57
     للاسماء
    0.57
    фициальный
    0.56
    righted
    0.52
     <=",
    0.51
    Activations Density 0.119%

    No Known Activations