© 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. 1-RES-MATRYOSHKA-DC
    7. 438
    Prev
    Next
    INDEX
    Explanations

    specific references to light or illumination

    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
    seteq
    -0.63
    原始内容存档于
    -0.63
     jPanel
    -0.63
    AndEndTag
    -0.63
    archiviato
    -0.60
    GEBURTS
    -0.59
     FishBase
    -0.59
    writeFieldEnd
    -0.58
    Datuak
    -0.58
    addPreferredGap
    -0.57
    POSITIVE LOGITS
     light
    4.88
    light
    4.41
     Light
    4.41
    Light
    4.34
     LIGHT
    4.06
    LIGHT
    3.75
    lights
    2.86
     licht
    2.84
     lights
    2.83
     lighter
    2.73
    Activations Density 0.446%

    No Known Activations