© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16649
    Prev
    Next
    INDEX
    Explanations

    references to the term "Twist" and its variations in context, particularly relating to biological processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rinehart
    -0.87
     Pell
    -0.82
    )("
    -0.81
    HCC
    -0.78
    Sentry
    -0.78
     familiari
    -0.78
     Kearns
    -0.78
     Agassi
    -0.77
    Kari
    -0.76
    tedra
    -0.75
    POSITIVE LOGITS
     Twist
    1.44
    Twist
    1.37
    twist
    1.36
     twist
    1.27
     Tw
    1.20
     twists
    1.19
    twisted
    1.16
    Twisted
    1.16
     twisting
    1.13
     Twisted
    1.13
    Activations Density 0.009%

    No Known Activations