© 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. 12-RES-MATRYOSHKA-DC
    7. 1314
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate levels or measurements of something

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
    %)$
    -0.87
    :{}
    -0.83
    تقاوى
    -0.82
     StringTokenizer
    -0.82
     OnDestroy
    -0.81
     ivelany
    -0.81
     Spree
    -0.78
     Nantes
    -0.77
    QPushButton
    -0.76
     Grimes
    -0.75
    POSITIVE LOGITS
     LEVEL
    1.73
     Level
    1.69
     level
    1.62
    LEVEL
    1.60
    Level
    1.53
    level
    1.52
     levels
    1.50
     Levels
    1.46
    Levels
    1.41
    levels
    1.37
    Activations Density 0.239%

    No Known Activations