© 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. 3768
    Prev
    Next
    INDEX
    Explanations

    occurrences of the "+" symbol in the text

    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
    ]<=
    -0.64
    openzeppelin
    -0.63
    --
    -0.62
     kasarigan
    -0.57
    .--
    -0.57
    gatsby
    -0.56
    ",$
    -0.52
    "]=
    -0.52
    例文帳に追加
    -0.52
    HomeAsUp
    -0.51
    POSITIVE LOGITS
     +
    1.63
     $+$
    1.17
     plus
    1.06
    $+$
    1.04
     $+\
    1.00
     плюс
    0.98
     +"
    0.94
     +.
    0.94
     PLUS
    0.93
    plus
    0.92
    Activations Density 0.113%

    No Known Activations