© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 978
    Prev
    Next
    INDEX
    Explanations

    references to chemical buffers and solutions containing sodium with specific anions or compounds

    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
    ChildScrollView
    -0.81
    UpInside
    -0.73
    Tembelea
    -0.64
    +#+
    -0.63
    DockStyle
    -0.62
    HVAC
    -0.62
     Cassini
    -0.59
    godic
    -0.58
    orianCalendar
    -0.57
     
    -0.57
    POSITIVE LOGITS
     hydrogen
    1.27
     nitrogen
    1.27
     sodium
    1.23
     potassium
    1.18
     calcium
    1.13
     Nitrogen
    1.03
     methyl
    1.02
     Hydrogen
    1.01
     ammonium
    1.01
     Sodium
    1.00
    Activations Density 0.912%

    No Known Activations