© 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. 24-RES-MATRYOSHKA-DC
    7. 309
    Prev
    Next
    INDEX
    Explanations

    usages of the word "have" including "has", "have", "haven't", but not "having"

    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.24.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.24.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
    setVerticalGroup
    -0.70
    endphp
    -0.66
    CompilerServices
    -0.64
    Was
    -0.62
    ropractic
    -0.61
    собенно
    -0.59
    hiel
    -0.59
    owol
    -0.59
     knew
    -0.57
    
    -0.57
    POSITIVE LOGITS
     been
    2.16
    been
    1.52
     BEEN
    1.32
     gotten
    1.31
     gone
    1.29
     come
    1.21
     become
    1.20
    Been
    1.20
     Been
    1.17
     fallen
    1.16
    Activations Density 1.684%

    No Known Activations