© 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. 24-RES-MATRYOSHKA-DC
    7. 268
    Prev
    Next
    INDEX
    Explanations

    scientific laboratory procedures

    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
    Not in Any Lists

    No Comments

    Negative Logits
     nogal
    -0.56
     estimés
    -0.54
    Comparing
    -0.53
    ácara
    -0.52
    Conclusión
    -0.50
    mybatisplus
    -0.50
    Compared
    -0.50
    XMLSchema
    -0.50
     Compared
    -0.49
    CMY
    -0.49
    POSITIVE LOGITS
     then
    0.81
    then
    0.66
     Затем
    0.65
     overnight
    0.63
     kemudian
    0.63
     followed
    0.61
     Daarna
    0.60
     immediately
    0.60
     ثم
    0.60
     затем
    0.60
    Activations Density 1.787%

    No Known Activations