© 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. 3-RES-MATRYOSHKA-DC
    7. 3121
    Prev
    Next
    INDEX
    Explanations

    the word "temporary" which it often finds in legal contexts

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thụ
    -0.62
     rigueur
    -0.60
    món
    -0.59
     Heim
    -0.55
     Determin
    -0.54
     Martino
    -0.54
     올
    -0.54
     acide
    -0.54
     comen
    -0.53
    INTERVAL
    -0.52
    POSITIVE LOGITS
     temporary
    3.22
     Temporary
    3.00
    Temporary
    2.92
    temporary
    2.89
     temporarily
    2.63
     temporaire
    2.48
    tempor
    2.14
     Tempor
    2.11
     tijde
    1.97
     tempor
    1.96
    Activations Density 0.029%

    No Known Activations