© 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. 18-RES-MATRYOSHKA-DC
    7. 196
    Prev
    Next
    INDEX
    Explanations

    the word "following."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     genoeg
    -0.61
    ंत्री
    -0.60
    yet
    -0.56
    Hentet
    -0.54
     acrylique
    -0.52
     különböz
    -0.52
     yet
    -0.52
    しかも
    -0.51
     للغاية
    -0.51
     propio
    -0.51
    POSITIVE LOGITS
     thing
    0.91
    tagHelper
    0.73
     situation
    0.72
    mentioned
    0.72
     تضيفلها
    0.71
    脚注の使い方
    0.69
     scenario
    0.68
     arrangement
    0.68
     two
    0.67
    rungsseite
    0.65
    Activations Density 1.376%

    No Known Activations