© 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. 19201
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate comparisons or assessments of quantities and qualities

    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
    
    -0.52
    CppCodeGen
    -0.46
     apl
    -0.45
     action
    -0.44
    GU
    -0.44
    action
    -0.43
    Xiv
    -0.43
    GG
    -0.42
    cog
    -0.41
    com
    -0.41
    POSITIVE LOGITS
     Мексичка
    0.93
    ConstraintMaker
    0.74
    SaveChangesAsync
    0.66
    enumi
    0.65
    terness
    0.65
    usermodel
    0.65
     ujednoznacz
    0.65
    ///</
    0.65
    utilisons
    0.65
     Bioaccumulative
    0.62
    Activations Density 0.306%

    No Known Activations