© 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. 5102
    Prev
    Next
    INDEX
    Explanations

    references to scientific publications, technical concepts, and formal mathematical terminology

    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
    styleType
    -0.86
     gynhyrchwyd
    -0.75
     snippetHide
    -0.74
    GTCX
    -0.72
     transfieras
    -0.70
    mockMvc
    -0.69
    MarshalTo
    -0.68
    nonatomic
    -0.68
     surla
    -0.65
    ).]
    -0.65
    POSITIVE LOGITS
     cucchia
    0.55
     crescere
    0.55
     vérit
    0.55
     isolado
    0.54
     esempi
    0.53
     leçons
    0.52
     gomma
    0.50
     erreurs
    0.50
     metodi
    0.49
    中海
    0.49
    Activations Density 0.691%

    No Known Activations