© 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. 1623
    Prev
    Next
    INDEX
    Explanations

    statistical analysis and comparison of patient data

    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
    rungsseite
    -0.73
     propOrder
    -0.73
    principalTable
    -0.68
     PLWABN
    -0.67
     pinulongan
    -0.66
     createState
    -0.66
    setVerticalGroup
    -0.65
    
    -0.65
    NameInMap
    -0.60
    abestanden
    -0.60
    POSITIVE LOGITS
     compared
    3.73
    compared
    3.19
     Compared
    2.81
    Compared
    2.67
     compare
    2.55
     versus
    2.45
     vs
    2.44
     dibandingkan
    2.42
     compares
    2.34
     comparison
    2.31
    Activations Density 2.222%

    No Known Activations