© 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. 17870
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe states of being or conditions

    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
     AttributeSet
    -0.88
    ftagPool
    -0.83
     handleMessage
    -0.77
     oprot
    -0.70
    Geplaatst
    -0.70
    InitVars
    -0.69
     "..\..\..\
    -0.68
     ProtoMessage
    -0.68
    AddTagHelper
    -0.68
    ViewFeatures
    -0.68
    POSITIVE LOGITS
     Too
    0.89
     too
    0.87
    Too
    0.80
     TOO
    0.79
    too
    0.72
    TOO
    0.67
     zbyt
    0.57
     terlalu
    0.57
     elegans
    0.55
     for
    0.54
    Activations Density 0.035%

    No Known Activations