© 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. 2660
    Prev
    Next
    INDEX
    Explanations

    a mix of words and phrases related to research studies, academic papers, social issues, and food science.

    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
    oneofs
    -0.58
    AutoScaleMode
    -0.53
     ویکی‌پدیا
    -0.52
    Népesség
    -0.51
    awtextra
    -0.50
     bVar
    -0.49
    AnimationsModule
    -0.48
    bitat
    -0.47
     resultCode
    -0.47
    AfterClass
    -0.46
    POSITIVE LOGITS
     stronger
    2.03
     simpler
    1.93
     better
    1.93
     harder
    1.91
     easier
    1.88
     bardziej
    1.88
     clearer
    1.84
    훨
    1.84
    better
    1.84
     bigger
    1.84
    Activations Density 4.223%

    No Known Activations