© 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. 130
    Prev
    Next
    INDEX
    Explanations

    the verb "have" or contractions containing "have"

    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
    MessageTagHelper
    -0.73
    :✨
    -0.71
    setVerticalGroup
    -0.70
    parsedMessage
    -0.70
     متعلقه
    -0.69
     écl
    -0.69
     endif
    -0.68
     prosecute
    -0.66
     Wikiseite
    -0.66
     antworte
    -0.65
    POSITIVE LOGITS
     been
    1.79
    been
    1.20
     had
    1.11
     gotten
    1.11
     BEEN
    1.02
     gone
    1.02
     undergone
    1.00
     got
    0.96
     Been
    0.93
    Been
    0.92
    Activations Density 1.916%

    No Known Activations