© 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. 3740
    Prev
    Next
    INDEX
    Explanations

    expressions of conditionality or dependence in text

    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
    مكن
    -0.71
     finally
    -0.67
    reszcie
    -0.67
    cydow
    -0.66
    pired
    -0.63
    FileDialog
    -0.61
    躇
    -0.61
    pshots
    -0.60
     наконец
    -0.60
    ❤❤
    -0.59
    POSITIVE LOGITS
     unless
    2.73
    Unless
    2.63
     Unless
    2.61
    unless
    2.56
    除非
    1.70
     kecuali
    1.19
     sauf
    0.99
     lest
    0.87
     Either
    0.75
     MainAxisSize
    0.72
    Activations Density 0.007%

    No Known Activations