© 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. 3-RES-MATRYOSHKA-DC
    7. 120
    Prev
    Next
    INDEX
    Explanations

    words related to concepts, statements, and observations

    oai_token-act-pair · gemini-2.0-flash
    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
    Datuak
    -0.94
     számára
    -0.94
     mijne
    -0.94
     tevens
    -0.91
    共に
    -0.90
     ибо
    -0.90
     لئے
    -0.90
    ként
    -0.88
    Награды
    -0.88
     ранее
    -0.87
    POSITIVE LOGITS
     thing
    1.08
     things
    1.05
     thought
    0.96
    things
    0.96
     thinks
    0.95
     idea
    0.94
     way
    0.91
     think
    0.86
    talk
    0.83
     Thing
    0.82
    Activations Density 18.071%

    No Known Activations