© 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. 3-RES-MATRYOSHKA-DC
    7. 1784
    Prev
    Next
    INDEX
    Explanations

    instances of the word "calculate" and related words

    oai_token-act-pair · gemini-2.0-flash
    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
     Ceramby
    -0.63
     andata
    -0.59
     broadest
    -0.54
    ʺ
    -0.53
     araw
    -0.52
     Intens
    -0.52
     Engel
    -0.52
     Häufig
    -0.52
     Corée
    -0.51
     Diretto
    -0.51
    POSITIVE LOGITS
     calculate
    2.22
     calculating
    2.17
     Calculate
    2.14
     calculation
    2.13
     calculated
    2.06
    Calculate
    2.05
     calculates
    2.03
     calcul
    2.02
     calculations
    2.00
    calculated
    1.96
    Activations Density 0.334%

    No Known Activations