© 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. 26052
    Prev
    Next
    INDEX
    Explanations

    words associated with citations or references in academic papers

    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
    ktop
    -0.59
    rsiniz
    -0.52
    MethodManager
    -0.52
    SOUNDBITE
    -0.50
     CURIAM
    -0.50
     remarquable
    -0.49
    ★★★★★
    -0.48
     Pollutant
    -0.48
     exemplaires
    -0.48
     positions
    -0.48
    POSITIVE LOGITS
     @"/
    0.63
     ExecuteAsync
    0.56
    RunAsync
    0.54
    SizeF
    0.51
     lenker
    0.50
    itore
    0.49
    ImageContext
    0.49
     AssemblyVersion
    0.48
    OrBuilder
    0.47
    omitempty
    0.47
    Activations Density 0.028%

    No Known Activations