© 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. 151
    Prev
    Next
    INDEX
    Explanations

    words having to do with the supernatural, mythology, divinity, and general fantasticalness.

    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
     flannel
    -0.62
    RectangleBorder
    -0.62
    Guys
    -0.60
     pessi
    -0.60
     sparsely
    -0.59
     Leute
    -0.59
     particularly
    -0.58
     personel
    -0.57
     Leuten
    -0.57
    沓
    -0.57
    POSITIVE LOGITS
     dreams
    1.00
     treasures
    1.00
    GEBURTSDATUM
    0.96
     dream
    0.89
     secrets
    0.89
     Invention
    0.89
     treasure
    0.88
     invention
    0.87
     heroes
    0.85
     mondial
    0.85
    Activations Density 9.385%

    No Known Activations