© 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. 0-RES-MATRYOSHKA-DC
    7. 12095
    Prev
    Next
    INDEX
    Explanations

    references to spirits or spiritual entities

    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
    PerformLayout
    -0.59
    GraphicsUnit
    -0.59
    ViewFeatures
    -0.58
    DebuggerNonUser
    -0.57
    SharedDtor
    -0.56
    LookAnd
    -0.56
    featureID
    -0.55
    abestanden
    -0.54
    ラク
    -0.54
    ChildScrollView
    -0.54
    POSITIVE LOGITS
     spirits
    3.30
     Spirits
    2.69
     SPIR
    1.55
    Spir
    1.52
    spir
    1.48
     espírit
    1.25
     esprits
    0.99
     morale
    0.80
     ghosts
    0.79
    SPIR
    0.73
    Activations Density 0.004%

    No Known Activations