© 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. 15431
    Prev
    Next
    INDEX
    Explanations

    references to photons in various contexts

    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
    resolve
    -0.58
    IMPORT
    -0.56
    Sh
    -0.54
    res
    -0.53
     Fürst
    -0.53
    p
    -0.53
    Nh
    -0.52
     Ih
    -0.52
    lus
    -0.52
     orto
    -0.52
    POSITIVE LOGITS
     photons
    1.65
     photon
    1.59
     Photon
    1.41
    photon
    1.38
    Photon
    1.34
    Sucesor
    1.02
     foton
    0.95
    Tikang
    0.93
    AccessorTable
    0.92
     raiſ
    0.92
    Activations Density 0.005%

    No Known Activations