© 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. 22-RES-MATRYOSHKA-DC
    7. 2301
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to a process or procedure

    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.22.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.22.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
     surla
    -0.61
     pinulongan
    -0.55
    Distribuzione
    -0.55
     HasFactory
    -0.52
     táo
    -0.50
    KeySpec
    -0.50
     Rigidbody
    -0.48
     SqlDbType
    -0.48
     Erfindung
    -0.47
    appan
    -0.47
    POSITIVE LOGITS
     process
    3.53
    process
    3.13
     Process
    2.97
    Process
    2.86
     PROCESS
    2.73
     processes
    2.61
     proceso
    2.59
     processus
    2.58
     processo
    2.53
    PROCESS
    2.38
    Activations Density 0.670%

    No Known Activations