© 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. 1718
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and research findings

    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
     Fawcett
    -0.68
    Tes
    -0.63
     Nordrhein
    -0.63
     Newbury
    -0.60
    s
    -0.60
     Priscilla
    -0.60
    ğe
    -0.60
    util
    -0.59
     Oskar
    -0.59
    AspNetCore
    -0.59
    POSITIVE LOGITS
     studies
    1.12
     Study
    1.10
    STUDY
    1.10
    study
    1.09
    studies
    1.05
     study
    1.05
    Study
    1.03
     Studies
    0.96
     STUDY
    0.96
    STUDIES
    0.93
    Activations Density 0.499%

    No Known Activations