© 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. 2-RES-MATRYOSHKA-DC
    7. 6774
    Prev
    Next
    INDEX
    Explanations

    references to aquatic predators and related marine life

    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
    Géographie
    -0.67
     Animate
    -0.60
    createServer
    -0.58
     Raceway
    -0.57
    lacht
    -0.56
    +:+
    -0.56
     saites
    -0.56
    illable
    -0.55
     Scramble
    -0.54
     Paglinawan
    -0.54
    POSITIVE LOGITS
     zien
    0.50
     délic
    0.50
     segno
    0.50
     åt
    0.49
     malheureusement
    0.47
    onActivityResult
    0.47
     élé
    0.46
     gelten
    0.46
    iostream
    0.46
     Él
    0.45
    Activations Density 0.515%

    No Known Activations