© 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. 12-RES-MATRYOSHKA-DC
    7. 1333
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and actions that demonstrate changes or transitions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.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
     tomorrow
    -0.72
     vzduchu
    -0.69
    nolia
    -0.66
    makeConstraints
    -0.64
     areia
    -0.64
     künftig
    -0.63
    tomorrow
    -0.60
     AQ
    -0.60
     Samara
    -0.60
    antMatchers
    -0.59
    POSITIVE LOGITS
    oved
    0.90
     went
    0.90
    twas
    0.88
     CAME
    0.87
     died
    0.87
     did
    0.85
    =$?
    0.84
    came
    0.84
     WENT
    0.83
     came
    0.83
    Activations Density 1.678%

    No Known Activations