© 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. 0-RES-MATRYOSHKA-DC
    7. 11874
    Prev
    Next
    INDEX
    Explanations

    references to the superexchange interaction or superexchange coupling

    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
    ########.
    -0.84
    Geplaatst
    -0.74
    StoryboardSegue
    -0.69
    Filmographie
    -0.69
     >=",
    -0.67
     Waterhouse
    -0.66
     acquittal
    -0.65
     RSSSF
    -0.63
    ANTAGES
    -0.63
    Ljava
    -0.62
    POSITIVE LOGITS
     sup
    1.98
     Frankfurt
    0.79
    caster
    0.75
    casts
    0.73
     Ricci
    0.65
    Frankfurt
    0.64
     plaster
    0.59
     spasms
    0.59
     supuesto
    0.55
     Plaster
    0.54
    Activations Density 0.004%

    No Known Activations