© 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. 889
    Prev
    Next
    INDEX
    Explanations

    references to supplementary material

    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
     Grossman
    -0.52
     Etats
    -0.49
    JspWriter
    -0.48
    劫
    -0.46
    Packard
    -0.44
    Label
    -0.44
    Bissau
    -0.44
    IContainer
    -0.43
    nelson
    -0.43
    moil
    -0.43
    POSITIVE LOGITS
    lementary
    4.47
     complementary
    2.78
     Complementary
    2.61
     Supplementary
    2.39
     supplementary
    2.36
     complement
    2.23
    Supplementary
    2.23
     Complement
    2.20
    complement
    2.13
     complements
    2.06
    Activations Density 0.207%

    No Known Activations