© 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. 6789
    Prev
    Next
    INDEX
    Explanations

    references to computations or calculating something

    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
     Sarm
    -0.87
     contextLoads
    -0.85
    expandindo
    -0.84
     Tacitus
    -0.80
     Nara
    -0.79
     Nazar
    -0.78
    Datuak
    -0.74
     draughts
    -0.73
     ostrich
    -0.72
    AnchorStyles
    -0.72
    POSITIVE LOGITS
     compute
    1.97
    compute
    1.92
    Compute
    1.91
     Compute
    1.85
     computes
    1.63
     computed
    1.60
     computation
    1.56
     Computation
    1.42
    Computation
    1.41
    computed
    1.35
    Activations Density 0.023%

    No Known Activations