© 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. 12885
    Prev
    Next
    INDEX
    Explanations

    the mention of a specific idea or concept

    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
     concepts
    -1.45
     concept
    -1.44
     Concept
    -1.25
    concept
    -1.23
     Concepts
    -1.21
    concepts
    -1.21
    Concept
    -1.15
    Concepts
    -1.15
     CONCEPT
    -1.13
     conceptos
    -1.03
    POSITIVE LOGITS
     ComVisible
    0.98
     noDo
    0.83
    unhofer
    0.81
    parsedMessage
    0.79
     Roskov
    0.78
    TagMode
    0.77
    FieldBuilder
    0.77
    LookAnd
    0.76
    DockStyle
    0.76
    ciclopedia
    0.75
    Activations Density 0.005%

    No Known Activations