© 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. 6-RES-MATRYOSHKA-DC
    7. 1246
    Prev
    Next
    INDEX
    Explanations

    phrases including the words "a little" or "a bit"

    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
    portál
    -0.51
    makeConstraints
    -0.50
    engarkan
    -0.49
     all
    -0.49
     most
    -0.49
    penet
    -0.49
    aufnahme
    -0.48
     suốt
    -0.48
     endless
    -0.47
    jarkan
    -0.47
    POSITIVE LOGITS
    slightly
    1.25
    Slightly
    1.25
    Slight
    1.22
     slightly
    1.21
     Slightly
    1.21
     Etwas
    1.21
     légèrement
    1.19
     trochę
    1.16
     Slight
    1.16
    Somewhat
    1.14
    Activations Density 0.407%

    No Known Activations