© 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. 466
    Prev
    Next
    INDEX
    Explanations

    the word "to" followed by helper verbs like be or get

    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
    ódó
    -0.72
     используя
    -0.62
    instancetype
    -0.57
    mighty
    -0.55
    ั่ง
    -0.55
     gearbeitet
    -0.54
    リエ
    -0.52
    fold
    -0.52
     طریق
    -0.52
    ISING
    -0.52
    POSITIVE LOGITS
     be
    1.08
     ensure
    1.04
     help
    0.97
     facilitate
    0.91
     enable
    0.86
     illustrate
    0.85
     achieve
    0.85
     avoid
    0.83
     prevent
    0.82
     accommodate
    0.82
    Activations Density 2.035%

    No Known Activations