© 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. 12-RES-MATRYOSHKA-DC
    7. 32352
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "following."

    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
    Negative Logits
    outState
    -0.78
    Tikang
    -0.68
    ForRow
    -0.61
    Pautan
    -0.60
     AssemblyCulture
    -0.59
    unnitel
    -0.58
    zsef
    -0.57
    sieur
    -0.55
    umfang
    -0.54
    ută
    -0.54
    POSITIVE LOGITS
    BindingResult
    0.68
    WithFormat
    0.58
     @"/
    0.57
    Apples
    0.57
     Sine
    0.55
    }();
    0.55
     المعرف
    0.55
     propi
    0.54
    ="@+
    0.54
    LabelTagHelper
    0.54
    Activations Density 0.014%

    No Known Activations