© 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. 1585
    Prev
    Next
    INDEX
    Explanations

    the word "well"

    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
     Affair
    -0.53
     hereof
    -0.52
    Filler
    -0.52
    iwa
    -0.50
     AppColors
    -0.50
     vertes
    -0.50
    ACI
    -0.49
    responseType
    -0.49
    WireFormat
    -0.48
    ുക
    -0.47
    POSITIVE LOGITS
     well
    0.66
    UNRELATED
    0.62
     StatelessWidget
    0.59
    存于互联网档案馆
    0.59
    Архівовано
    0.58
    èdia
    0.58
    ViewImports
    0.58
     unknownFields
    0.57
    DECREF
    0.55
     disambiguazione
    0.55
    Activations Density 0.051%

    No Known Activations