© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13050
    Prev
    Next
    INDEX
    Explanations

    references to specific performance measurements or metrics

    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
     Référence
    -0.66
    wpi
    -0.60
    GEBURTSDATUM
    -0.60
    bufio
    -0.59
    ActionCreators
    -0.58
    aarrggbb
    -0.56
    classnames
    -0.56
    photobucket
    -0.54
     generators
    -0.54
    ardia
    -0.53
    POSITIVE LOGITS
     Perf
    2.42
    perf
    2.36
     perf
    2.20
    Perf
    2.20
    PERF
    1.27
     Perfume
    1.04
     perfumes
    1.02
     perfume
    0.94
     perfusion
    0.89
    perfume
    0.77
    Activations Density 0.001%

    No Known Activations