© 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. 12-RES-MATRYOSHKA-DC
    7. 1510
    Prev
    Next
    INDEX
    Explanations

    phrases indicating different methods or approaches to accomplish a task

    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
    numerusform
    -1.01
     AssemblyCompany
    -0.95
    Datuak
    -0.84
    ölkerung
    -0.80
     Iri
    -0.80
     насељу
    -0.80
    aarrggbb
    -0.79
    silience
    -0.79
    TestingModule
    -0.78
    ựng
    -0.78
    POSITIVE LOGITS
     ways
    1.81
     way
    1.75
     Way
    1.75
     Ways
    1.73
     WAY
    1.64
     WAYS
    1.56
    Way
    1.55
    Ways
    1.54
    way
    1.28
     façon
    1.23
    Activations Density 0.446%

    No Known Activations