© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13498
    Prev
    Next
    INDEX
    Explanations

    references to the version number of a software or document

    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
     iſt
    -0.75
     Rev
    -0.69
     Efq
    -0.69
    ]")]
    -0.66
    &
    -0.61
    \\
    -0.60
     \\
    -0.59
     Forumite
    -0.58
    />";
    -0.58
     CanadaChoose
    -0.56
    POSITIVE LOGITS
    Rev
    1.17
    rev
    0.99
    REV
    0.90
    __(/*!
    0.77
    endpush
    0.66
    はじめに
    0.64
    NewUrlParser
    0.63
     scaricare
    0.62
    IntoConstraints
    0.59
     igång
    0.59
    Activations Density 0.001%

    No Known Activations