© 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. 2242
    Prev
    Next
    INDEX
    Explanations

    the forms of the word "attend."

    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
    /**
    -0.78
     Audiodateien
    -0.66
    \{\\
    -0.63
     Cleanser
    -0.62
     Gosling
    -0.59
    Filmografie
    -0.59
     Deak
    -0.59
    <?
    -0.58
     Kitchen
    -0.58
     Workspace
    -0.58
    POSITIVE LOGITS
     attend
    2.83
     attended
    2.83
     attending
    2.77
     Attending
    2.67
     attends
    2.58
     Attend
    2.56
     attendance
    2.42
    attended
    2.36
    Attend
    2.36
    attend
    2.27
    Activations Density 0.020%

    No Known Activations