© 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. 1672
    Prev
    Next
    INDEX
    Explanations

    verbs and verb phrases related to action or states

    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
     the
    -0.77
    they
    -0.72
     lui
    -0.69
     them
    -0.67
    them
    -0.66
    They
    -0.66
     They
    -0.65
     he
    -0.63
    he
    -0.62
    herself
    -0.60
    POSITIVE LOGITS
     his
    1.66
     their
    1.61
     seu
    1.58
     seus
    1.57
     sua
    1.51
     suas
    1.48
     your
    1.45
     své
    1.40
     my
    1.38
     ihrer
    1.34
    Activations Density 3.215%

    No Known Activations