© 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. 24-RES-MATRYOSHKA-DC
    7. 1469
    Prev
    Next
    INDEX
    Explanations

    latex commands

    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.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    umumkan
    -0.47
     zufolge
    -0.46
    ropoda
    -0.43
     khas
    -0.42
     retention
    -0.42
    برها
    -0.41
    criture
    -0.40
    roba
    -0.40
     Advantage
    -0.40
     melainkan
    -0.39
    POSITIVE LOGITS
    aligned
    0.85
    tagHelperRunner
    0.80
     initComponents
    0.79
    IntoConstraints
    0.76
    equation
    0.73
    align
    0.71
    AxisAlignment
    0.71
     оригіналу
    0.71
     autorytatywna
    0.70
     aligned
    0.69
    Activations Density 0.034%

    No Known Activations