© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 52
    Prev
    Next
    INDEX
    Explanations

    terms related to software development challenges and solution requirements

    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
     mesmos
    -0.70
     ansiedade
    -0.61
    rfloor
    -0.59
    odenal
    -0.59
    rawDesc
    -0.59
     meest
    -0.58
     médicaux
    -0.56
    WebpackPlugin
    -0.56
     solare
    -0.56
     refugiados
    -0.56
    POSITIVE LOGITS
     of
    1.21
     itſelf
    0.80
     ―――――
    0.74
    leſs
    0.70
    RectangleBorder
    0.68
     regarding
    0.65
     ――――――――
    0.65
     relationship
    0.65
     ofre
    0.63
     throughout
    0.63
    Activations Density 12.786%

    No Known Activations