© 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. 3936
    Prev
    Next
    INDEX
    Explanations

    references to various detailed manufacturing or technical techniques

    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
     technological
    -1.02
     technolog
    -0.95
     tecnológico
    -0.90
    Technological
    -0.86
     technology
    -0.82
     Technological
    -0.82
     Technology
    -0.78
    Technology
    -0.77
     tecnológica
    -0.77
     technologically
    -0.76
    POSITIVE LOGITS
     technique
    2.13
     Technique
    2.06
     TECHNIQUE
    2.05
     Techniques
    1.98
     TECHNIQUES
    1.88
    Technique
    1.87
     techniques
    1.84
    Techniques
    1.83
    technique
    1.82
    techniques
    1.74
    Activations Density 0.022%

    No Known Activations