© 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. 9604
    Prev
    Next
    INDEX
    Explanations

    settings related to cURL options in code

    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
     AspNetCore
    -0.66
    ViewFeatures
    -0.57
    Brainz
    -0.56
    ANCE
    -0.53
    awaiter
    -0.53
     ModelExpression
    -0.53
    antd
    -0.52
    detectChanges
    -0.51
    knex
    -0.50
    sstream
    -0.50
    POSITIVE LOGITS
     CURLOPT
    3.95
    CURLOPT
    2.98
    setopt
    1.08
    glEnable
    0.81
    CURL
    0.79
    nexpected
    0.73
    essoa
    0.65
    reht
    0.64
    __(/*!
    0.63
    Бахар
    0.63
    Activations Density 0.003%

    No Known Activations