© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4690
    Prev
    Next
    INDEX
    Explanations

    references to the concept of twisting or twisting ties, particularly variations of the word "twist."

    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
    原始内容存档于
    -0.73
    存于互联网档案馆
    -0.71
     nakalista
    -0.65
     Agassi
    -0.60
     Brem
    -0.59
     Gole
    -0.58
     Newell
    -0.57
     Ums
    -0.55
    ComponentModel
    -0.54
     Barns
    -0.54
    POSITIVE LOGITS
     twist
    3.08
    twist
    2.98
     Twist
    2.92
    Twist
    2.69
     twists
    2.64
     twisted
    2.59
     twisting
    2.47
    twisted
    2.41
     Twisted
    2.16
    Twisted
    1.92
    Activations Density 0.013%

    No Known Activations