© 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. 412
    Prev
    Next
    INDEX
    Explanations

    references to any or all in the context of searching, identifying, or highlighting inclusivity or generality

    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
     defaultstate
    -0.72
     للمعارف
    -0.68
    several
    -0.65
    Plusieurs
    -0.65
     several
    -0.64
    Several
    -0.63
    wijl
    -0.63
     two
    -0.63
    LabelTagHelper
    -0.62
    ientôt
    -0.62
    POSITIVE LOGITS
     any
    4.19
     Any
    3.75
    Any
    3.73
    any
    3.55
     ANY
    3.39
    ANY
    3.16
     cualquier
    2.89
     qualquer
    2.89
     anything
    2.88
    任何
    2.84
    Activations Density 0.404%

    No Known Activations