© 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. 1813
    Prev
    Next
    INDEX
    Explanations

    the word "treat" and related words, especially when followed by "with"

    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
     Anſ
    -1.13
     iſt
    -1.10
     doubtnut
    -1.09
     Efq
    -1.09
     auffi
    -1.05
     Reſ
    -1.05
     Monfieur
    -1.02
     Jefus
    -1.02
     ―――――
    -1.00
     myſelf
    -1.00
    POSITIVE LOGITS
     treat
    2.73
     treated
    2.73
     treating
    2.64
     Treat
    2.63
    treat
    2.48
    treated
    2.44
     treatment
    2.42
     TREAT
    2.36
     Treated
    2.33
    Treat
    2.31
    Activations Density 0.621%

    No Known Activations