© 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. 4329
    Prev
    Next
    INDEX
    Explanations

    references to the percentage of votes or support ставки

    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
    Traducción
    -0.69
    ptor
    -0.58
    databind
    -0.58
    کید
    -0.56
    EDEFAULT
    -0.54
     Astra
    -0.54
    -------------</
    -0.54
     Jock
    -0.53
    itability
    -0.52
     pre
    -0.52
    POSITIVE LOGITS
     Cent
    2.72
     cent
    2.69
    Cent
    2.66
    cent
    2.56
     CENT
    2.05
    ¢
    1.92
    CENT
    1.88
     cents
    1.73
     Cents
    1.67
     Centennial
    1.59
    Activations Density 0.024%

    No Known Activations