© 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. 22911
    Prev
    Next
    INDEX
    Explanations

    actions or processes that involve communication and planning

    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
    yarnpkg
    -0.71
    ToDecimal
    -0.59
     CURLOPT
    -0.56
     nahilalakip
    -0.56
    DebuggerNonUser
    -0.56
    GEBURTSDATUM
    -0.55
     لينك
    -0.55
    tono
    -0.54
    ICEF
    -0.54
    modb
    -0.54
    POSITIVE LOGITS
    Instead
    1.05
     Instead
    1.04
     instead
    1.00
    instead
    0.89
    tdessen
    0.89
     istället
    0.75
     zamiast
    0.75
     invece
    0.71
     plutôt
    0.67
     Rather
    0.65
    Activations Density 0.041%

    No Known Activations