© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 23629
    Prev
    Next
    INDEX
    Explanations

    words associated with request handling in a server-client interaction context

    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
     Gazetteer
    -0.57
    BindingResult
    -0.53
    SerializedSize
    -0.52
    BindView
    -0.51
     soeur
    -0.48
     кӀош
    -0.47
    ChromeDriver
    -0.46
     avulla
    -0.46
    Rhestr
    -0.45
     ligiloj
    -0.45
    POSITIVE LOGITS
     оригіналу
    0.71
     nahilalakip
    0.71
    YARD
    0.65
    principalTable
    0.63
    __":
    0.59
    ulose
    0.59
    /**
    0.58
    ]));
    0.57
    tamide
    0.57
    '));
    0.57
    Activations Density 0.020%

    No Known Activations