© 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. 1958
    Prev
    Next
    INDEX
    Explanations

    words that are either encouraging or describe something as easy to do or obtain.

    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
     infeliz
    -0.58
     unsuccessfully
    -0.56
     unsuccessful
    -0.54
    残念ながら
    -0.53
    PMailer
    -0.50
    GEBURTSDATUM
    -0.47
    どうやら
    -0.47
     necesariamente
    -0.47
     okuyayım
    -0.47
     inconclusive
    -0.47
    POSITIVE LOGITS
     easy
    2.19
     easily
    2.00
     easier
    1.96
    easy
    1.90
     Easily
    1.77
    easily
    1.77
    Easy
    1.75
     ease
    1.73
     Easy
    1.71
     fácil
    1.67
    Activations Density 3.686%

    No Known Activations