© 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-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 276
    Prev
    Next
    INDEX
    Explanations

    action verbs related to experimental and statistical processes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     اینکه
    -0.37
    OrUpdate
    -0.33
    //
    -0.32
    原始内容存档于
    -0.32
     Recently
    -0.32
    Recently
    -0.32
    <strong>
    -0.31
     используя
    -0.31
    @
    -0.31
    them
    -0.30
    POSITIVE LOGITS
     propOrder
    0.85
     zoude
    0.80
    majánló
    0.70
    ⤒
    0.69
     queſta
    0.68
     verhält
    0.65
     veranderen
    0.65
     contributes
    0.65
    wiliwch
    0.62
     hoort
    0.62
    Activations Density 5.421%

    No Known Activations