© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15255
    Prev
    Next
    INDEX
    Explanations

    phrases related to obtaining or revealing truth and insightful information

    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
     subprocess
    -0.58
     fubject
    -0.55
     otomatig
    -0.54
     ſtate
    -0.54
    "?>
    -0.54
     appearing
    -0.52
     itſelf
    -0.52
    keyDown
    -0.52
    rouge
    -0.52
     mouseY
    -0.52
    POSITIVE LOGITS
     ricev
    0.69
     Receive
    0.66
     mergeFrom
    0.66
    ActionCreators
    0.65
     receives
    0.63
     RECEIVE
    0.63
     receive
    0.62
     brunt
    0.61
    received
    0.60
     received
    0.59
    Activations Density 0.299%

    No Known Activations