© 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. 3324
    Prev
    Next
    INDEX
    Explanations

    descriptions of materials or methods related to chemical or structural characterization

    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
     CHAR
    -0.61
     Letter
    -0.59
    Vorlage
    -0.56
    LETTER
    -0.55
     letters
    -0.54
     stupid
    -0.54
     Letters
    -0.54
    Letter
    -0.54
    letters
    -0.52
    achable
    -0.51
    POSITIVE LOGITS
     characterized
    2.11
     characterised
    2.03
     characterizes
    1.74
     characterize
    1.73
     caractéris
    1.63
     characterizing
    1.41
     caracteriza
    1.20
     характеризу
    1.20
    character
    1.07
    Characterization
    1.05
    Activations Density 0.023%

    No Known Activations