© 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. 12-RES-MATRYOSHKA-DC
    7. 29698
    Prev
    Next
    INDEX
    Explanations

    references to software licensing information, specifically related to the GPL license

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelBuilder
    -0.60
    NameInMap
    -0.56
     Baj
    -0.55
     Stern
    -0.54
    Zitat
    -0.54
    ajemen
    -0.54
     Og
    -0.52
     הבי
    -0.52
    DOG
    -0.51
    liosis
    -0.51
    POSITIVE LOGITS
     GPL
    1.84
    GPL
    1.59
    gpl
    1.09
     ujednoznacz
    0.82
     disambiguazione
    0.71
     mpl
    0.69
    Bindable
    0.68
    Diwedd
    0.68
    *~*~
    0.67
    liferay
    0.66
    Activations Density 0.002%

    No Known Activations