© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10446
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions, equations, or calculations

    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
    Negative Logits
     الحره
    -1.06
     assume
    -0.98
    ">//
    -0.96
     assuming
    -0.90
    assume
    -0.87
    Assume
    -0.84
     assumes
    -0.84
     assumed
    -0.82
    Assumption
    -0.81
     Assumption
    -0.80
    POSITIVE LOGITS
     Suppose
    0.88
    oeil
    0.56
     BoxFit
    0.54
    ContentAlignment
    0.49
     thought
    0.47
    Thought
    0.47
    zkopf
    0.47
     Thought
    0.47
    DockStyle
    0.47
    udert
    0.47
    Activations Density 0.009%

    No Known Activations