© 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. 70
    Prev
    Next
    INDEX
    Explanations

    code, file paths, or command line instructions

    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
    ValueStyle
    -0.83
    تقاوى
    -0.71
     onPostExecute
    -0.69
     становника
    -0.68
    SuppressLint
    -0.65
    expandindo
    -0.60
     يتيمه
    -0.60
    TextHelper
    -0.59
    Carriera
    -0.57
    TextWatcher
    -0.57
    POSITIVE LOGITS
     server
    0.97
     service
    0.91
     servers
    0.87
     services
    0.81
     network
    0.79
     Server
    0.77
     client
    0.75
     Service
    0.74
     host
    0.73
    server
    0.73
    Activations Density 6.205%

    No Known Activations