© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15790
    Prev
    Next
    INDEX
    Explanations

    references to specific types of objects or concepts associated with certain identifiers or themes

    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
    RegistryLite
    -0.83
     TestBed
    -0.75
    UnknownFields
    -0.75
    TestBed
    -0.70
    elemField
    -0.68
    Geplaatst
    -0.67
     BoxFit
    -0.65
    AndEndTag
    -0.65
    ]})
    -0.65
     beginnetje
    -0.60
    POSITIVE LOGITS
    uch
    3.64
    UCH
    2.86
    uchi
    1.44
    uchs
    1.38
    ucha
    1.37
     uch
    1.34
    uche
    1.32
    uchy
    1.30
    uchin
    1.25
    ucher
    1.21
    Activations Density 0.001%

    No Known Activations