© 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. 4730
    Prev
    Next
    INDEX
    Explanations

    the explicit mention of dividing text or data into separate parts or entities

    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
     Isolation
    -1.04
     isolation
    -1.02
    isolation
    -0.90
    Isolation
    -0.87
    Hentet
    -0.86
     isolating
    -0.82
     Separation
    -0.82
     AssemblyCulture
    -0.82
     ISOL
    -0.82
     Isolated
    -0.79
    POSITIVE LOGITS
     separate
    2.42
    separate
    2.27
    Separate
    2.16
     Separate
    2.13
     seperate
    2.00
     separately
    1.90
     separado
    1.42
     SEPAR
    1.38
     terpisah
    1.34
     отдель
    1.21
    Activations Density 0.013%

    No Known Activations