© 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. 1605
    Prev
    Next
    INDEX
    Explanations

    items beginning with a colon or parenthesis

    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
     мәкал
    -1.00
    =$?
    -0.98
    脚注の使い方
    -0.96
     AssemblyProduct
    -0.95
     betweenstory
    -0.93
    MessageTagHelper
    -0.88
    abestanden
    -0.87
    хьтан
    -0.87
    InitVars
    -0.83
     Roskov
    -0.83
    POSITIVE LOGITS
     firstly
    1.16
     Firstly
    1.14
    ①
    1.13
     First
    1.09
     first
    1.02
    Firstly
    1.00
    •
    0.98
    1
    0.96
     •
    0.96
    一是
    0.96
    Activations Density 1.296%

    No Known Activations