© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 2825
    Prev
    Next
    INDEX
    Explanations

    the substring 'us' at the end of a word

    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
    bní
    -0.72
     purpoſe
    -0.66
     GTR
    -0.66
     Anſ
    -0.62
     myſelf
    -0.60
     ſind
    -0.58
    てる
    -0.56
    rzej
    -0.56
    ‍♀️
    -0.56
     raiſ
    -0.54
    POSITIVE LOGITS
    us
    2.94
    US
    2.19
    Us
    1.65
     Us
    1.52
     US
    1.51
     us
    1.48
    usnya
    1.24
    nus
    1.16
    usy
    1.13
    usan
    1.10
    Activations Density 0.070%

    No Known Activations