© 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. 12-RES-MATRYOSHKA-DC
    7. 22248
    Prev
    Next
    INDEX
    Explanations

    terms related to scattering phenomena

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -1.11
    SpringBootTest
    -1.04
     StatefulWidget
    -1.00
    PerformLayout
    -0.96
     Koran
    -0.93
     onCancelled
    -0.93
     AssemblyTitle
    -0.92
     känd
    -0.91
    tvguidetime
    -0.90
    verläs
    -0.89
    POSITIVE LOGITS
     scattering
    1.16
     Scattering
    1.03
    Scatter
    0.96
     scatter
    0.93
    scattering
    0.90
     Scatter
    0.77
    scatter
    0.71
     scattered
    0.70
     Tur
    0.65
    ATTER
    0.63
    Activations Density 0.006%

    No Known Activations