© 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. 4916
    Prev
    Next
    INDEX
    Explanations

    references to technology platforms or hardware that are commonly used as starter or learning tools

    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
     AssemblyCompany
    -0.67
    esri
    -0.60
    ợ
    -0.58
    lehem
    -0.56
    TagMode
    -0.55
    ostomy
    -0.54
    ecy
    -0.54
     fax
    -0.53
     Gutenberg
    -0.53
    agna
    -0.53
    POSITIVE LOGITS
     platform
    3.56
    Platform
    3.45
     Platform
    3.42
    platform
    3.41
     platforms
    3.30
     Platforms
    3.16
     PLATFORM
    3.14
     Plattform
    2.83
    platforms
    2.77
     plataforma
    2.75
    Activations Density 0.010%

    No Known Activations