© 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. 6-RES-MATRYOSHKA-DC
    7. 403
    Prev
    Next
    INDEX
    Explanations

    the word "on" followed by the word "the"

    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
    endregion
    -0.87
    原始内容存档于
    -0.79
     useRef
    -0.79
     ElementRef
    -0.70
    inflater
    -0.68
    ActionPerformed
    -0.66
    liani
    -0.66
    ↵↵↵
    -0.66
    Spoiler
    -0.66
     authentique
    -0.66
    POSITIVE LOGITS
     on
    1.74
     On
    1.60
     ON
    1.51
    On
    1.48
     behalf
    1.26
    isOn
    1.21
    on
    1.16
     وعلى
    1.16
    addOn
    1.05
     на
    1.00
    Activations Density 1.802%

    No Known Activations