© 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. 2-RES-MATRYOSHKA-DC
    7. 4398
    Prev
    Next
    INDEX
    Explanations

    references to specific salient objects or concepts

    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
     things
    -1.33
    Things
    -1.10
     Things
    -1.09
    things
    -0.91
     THINGS
    -0.85
     Dinge
    -0.75
     saker
    -0.71
     items
    -0.68
     matters
    -0.68
     cosas
    -0.67
    POSITIVE LOGITS
     thing
    1.86
     THING
    1.59
     Thing
    1.45
    thing
    1.30
    Thing
    1.27
    THING
    1.02
     thingy
    0.91
     cosa
    0.75
    UrlResolution
    0.75
    StructEnd
    0.75
    Activations Density 0.012%

    No Known Activations