© 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. 2525
    Prev
    Next
    INDEX
    Explanations

    mentions of seizing power, control, land, items or opportunities

    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
    立
    -0.52
     campagnes
    -0.51
    Posted
    -0.50
    gtest
    -0.50
    inot
    -0.49
    ington
    -0.48
    dolu
    -0.47
     Woodford
    -0.47
    ceton
    -0.45
    ॰
    -0.45
    POSITIVE LOGITS
     seize
    1.63
     seized
    1.59
     grabs
    1.56
     seizing
    1.56
     grabbed
    1.52
     grab
    1.45
     grasped
    1.45
     grasp
    1.43
     grabbing
    1.43
     grasping
    1.41
    Activations Density 0.590%

    No Known Activations