© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15547
    Prev
    Next
    INDEX
    Explanations

    references to the isotropic property of materials or systems

    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
    rungsseite
    -0.62
    DropColumn
    -0.47
     wrong
    -0.46
    TimerTask
    -0.46
     her
    -0.46
     serious
    -0.43
    dres
    -0.43
    ković
    -0.42
     complicated
    -0.42
     major
    -0.40
    POSITIVE LOGITS
     isotropic
    3.72
     anisotropic
    1.45
    otropic
    0.91
    otropy
    0.87
     EconPapers
    0.85
     anisotropy
    0.82
    醐
    0.80
     InputDecoration
    0.76
    DrawerToggle
    0.75
    InputBorder
    0.74
    Activations Density 0.001%

    No Known Activations