© 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. 22-RES-MATRYOSHKA-DC
    7. 7
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to debate or disagreement.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
     asisten
    -0.71
     eccell
    -0.70
     '\\;'
    -0.69
     houſe
    -0.68
     officiellement
    -0.67
     przeznac
    -0.66
     AssemblyCompany
    -0.66
     consecutively
    -0.66
     eseguire
    -0.66
     découver
    -0.66
    POSITIVE LOGITS
     logical
    0.91
     obvious
    0.87
     clearly
    0.86
     clear
    0.84
     implicit
    0.82
     understandable
    0.81
     nuanced
    0.80
     perhaps
    0.80
     argument
    0.79
     logic
    0.77
    Activations Density 12.528%

    No Known Activations