© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13189
    Prev
    Next
    INDEX
    Explanations

    patterns of information coherence within quantum states

    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
    ence
    -0.85
     रेटिंग
    -0.53
    gdx
    -0.51
    neous
    -0.50
    ience
    -0.49
    rance
    -0.48
    Paper
    -0.48
    ztály
    -0.47
    WireFormatLite
    -0.47
    upaten
    -0.46
    POSITIVE LOGITS
    ences
    3.02
    ENCES
    1.42
    adaptiveStyles
    0.78
     AssemblyCompany
    0.77
    تقاوى
    0.70
    entee
    0.68
    ConstraintMaker
    0.68
     JpaRepository
    0.68
    
    0.66
     fences
    0.65
    Activations Density 0.001%

    No Known Activations