© 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. 0-RES-MATRYOSHKA-DC
    7. 15187
    Prev
    Next
    INDEX
    Explanations

    references to algebraic expressions 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
     pleaſure
    -0.65
     صوتيه
    -0.65
    AddTagHelper
    -0.65
    TemporalType
    -0.61
    EndProject
    -0.61
     חיצוניים
    -0.60
    chot
    -0.59
     JpaRepository
    -0.57
     algebras
    -0.56
     мәкал
    -0.56
    POSITIVE LOGITS
     algebraic
    2.75
     Algebraic
    2.20
    — 
    0.56
     manquer
    0.56
     voeren
    0.55
    Algebra
    0.54
    ampiyon
    0.53
    algebra
    0.51
    quete
    0.50
     الحره
    0.50
    Activations Density 0.001%

    No Known Activations