© 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. 143
    Prev
    Next
    INDEX
    Explanations

    adverbs

    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
     finalement
    -0.65
     addirittura
    -0.64
    もはや
    -0.63
    hydrogenase
    -0.61
     sicuramente
    -0.60
     schließlich
    -0.59
    clang
    -0.59
     persino
    -0.59
     infine
    -0.56
    ValueGeneration
    -0.56
    POSITIVE LOGITS
    IVEREF
    0.85
    AsUp
    0.80
    RegistryLite
    0.76
     оригіналу
    0.74
     تضيفلها
    0.72
     nahilalakip
    0.72
    دانشنامهٔ
    0.72
    mybatisplus
    0.69
    arily
    0.66
    adpleegd
    0.66
    Activations Density 2.406%

    No Known Activations