© 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
    2. Gemma-2-2B
    3. 3-RES-MATRYOSHKA-DC
    4. 3093
    Prev
    Next
    INDEX
    Explanations

    words that reduce or have a negative impact

    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
     weeping
    -0.65
     praying
    -0.63
    gridx
    -0.63
     constipation
    -0.62
     rectum
    -0.62
     defaultstate
    -0.61
     infestations
    -0.60
    !("{}",
    -0.60
     hugging
    -0.60
     diagonally
    -0.60
    POSITIVE LOGITS
     dimming
    0.87
     dimmed
    0.84
     dampen
    0.82
     AssemblyCulture
    0.80
     dim
    0.76
    Dim
    0.73
     dimmer
    0.72
     damp
    0.69
     DIM
    0.68
     Dim
    0.67
    Activations Density 0.816%

    No Known Activations