© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    descriptions or references to tape dispensers

    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
    USAL
    -0.58
     هيا
    -0.58
     Har
    -0.55
    ']);
    -0.54
    jö
    -0.54
     Sal
    -0.54
    ">'.$
    -0.54
     Ro
    -0.52
     نف
    -0.52
    脚注の使い方
    -0.52
    POSITIVE LOGITS
     tape
    3.81
     Tape
    3.41
    tape
    3.22
    Tape
    3.17
     tapes
    3.08
     TAPE
    3.05
    tapes
    2.34
     taped
    2.31
     taping
    2.17
     Tapes
    2.16
    Activations Density 0.010%

    No Known Activations