© 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. 670
    Prev
    Next
    INDEX
    Explanations

    the verb "is" or "was/were" as part of a passive construction.

    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
    >--}}
    -0.64
    iented
    -0.61
    ipedi
    -0.59
     interact
    -0.57
     different
    -0.57
    tled
    -0.56
    chett
    -0.56
     flat
    -0.55
    }`}>
    -0.53
    〢
    -0.53
    POSITIVE LOGITS
     inplace
    0.62
     فريبيس
    0.60
    <bos>
    0.57
     ensued
    0.53
    UnknownFieldSet
    0.52
     وجود
    0.52
     empleados
    0.51
     présentes
    0.50
    ConstraintMaker
    0.49
    addContainerGap
    0.49
    Activations Density 0.854%

    No Known Activations