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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 16492
    Prev
    Next
    INDEX
    Explanations

    instructions related to enabling and configuring settings for user accessibility features

    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
     NSCoder
    -0.66
    rungsseite
    -0.60
    onAttach
    -0.60
     مُعرِّف
    -0.59
    URLException
    -0.58
    RegistryLite
    -0.56
     onCreateView
    -0.54
    Referencer
    -0.51
    closedir
    -0.50
    tagext
    -0.50
    POSITIVE LOGITS
     strto
    0.66
     policies
    0.65
    pogon
    0.65
    Autoritní
    0.62
     policy
    0.60
     limit
    0.58
     Dmit
    0.56
     Policies
    0.56
    Def
    0.56
     Tactical
    0.56
    Activations Density 0.138%

    No Known Activations