© 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. 2-RES-MATRYOSHKA-DC
    7. 6020
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reply."

    oai_token-act-pair · gpt-4.1-nano
    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
     nastro
    -0.84
    UnsafeEnabled
    -0.81
     kaynağından
    -0.75
    Ecco
    -0.73
     WAC
    -0.73
    مصادر
    -0.72
     newBuilder
    -0.71
    endpush
    -0.71
    AnchorTagHelper
    -0.70
    onedDateTime
    -0.69
    POSITIVE LOGITS
     reply
    2.55
    Reply
    2.52
    reply
    2.52
     Reply
    2.45
     replies
    2.11
     replied
    2.02
     REPLY
    2.00
     replying
    1.91
     Replies
    1.74
    REPLY
    1.73
    Activations Density 0.007%

    No Known Activations