© 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. 18-RES-MATRYOSHKA-DC
    7. 910
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific studies, fire zones, economic losses, or mechanical apparatuses.

    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.18.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.18.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
    CharStream
    -0.60
    RegressionTest
    -0.54
    readValue
    -0.53
    ことができ
    -0.52
     but
    -0.52
    biendo
    -0.52
    AtIndexPath
    -0.52
    しかも
    -0.50
    PAREN
    -0.50
    TO
    -0.48
    POSITIVE LOGITS
     чтобы
    1.76
     כדי
    1.66
     để
    1.59
     щоб
    1.49
    เพื่อ
    1.42
     upang
    1.41
     affinch
    1.40
     afin
    1.39
     чтоб
    1.30
     żeby
    1.21
    Activations Density 3.469%

    No Known Activations