© 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. 2-RES-MATRYOSHKA-DC
    7. 3559
    Prev
    Next
    INDEX
    Explanations

    references to immune activity

    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
     calendriers
    -0.60
    AndEndTag
    -0.58
    رشف
    -0.57
    脚注の使い方
    -0.56
    osoba
    -0.50
     mano
    -0.49
    Географиясе
    -0.49
    服
    -0.49
    tamount
    -0.47
    tamol
    -0.47
    POSITIVE LOGITS
    ore
    3.70
    ORE
    2.84
    oré
    1.91
    ores
    1.91
    ORES
    1.76
    Ore
    1.69
     ore
    1.68
     Ore
    1.64
     ORE
    1.59
    oreo
    1.48
    Activations Density 0.012%

    No Known Activations