© 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. 12455
    Prev
    Next
    INDEX
    Explanations

    the magnitude of variability or difference, such as measurement errors or fluctuations

    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
    imensional
    -0.65
    mybatisplus
    -0.63
    ofag
    -0.63
    NOPQRST
    -0.62
    mtrl
    -0.60
     تانيه
    -0.59
     חיצוניים
    -0.58
     StatelessWidget
    -0.57
    yntaxException
    -0.56
     المعيارى
    -0.56
    POSITIVE LOGITS
    +/-
    2.06
     AssemblyCulture
    0.62
    Bref
    0.59
    rshire
    0.57
     Commencez
    0.57
    IContainer
    0.57
    tinta
    0.57
    getahuan
    0.56
     Lenses
    0.53
     lenses
    0.53
    Activations Density 0.002%

    No Known Activations