© 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. 18-RES-MATRYOSHKA-DC
    7. 633
    Prev
    Next
    INDEX
    Explanations

    technical language related to noise and error in scientific modeling and measurement.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Formik
    -0.56
    avras
    -0.56
    ConstraintMaker
    -0.55
     facie
    -0.52
     ujednoznacz
    -0.51
     Zust
    -0.50
     Benth
    -0.49
     удо
    -0.49
    сылкі
    -0.49
    SequentialGroup
    -0.49
    POSITIVE LOGITS
     extraneous
    0.82
     factors
    0.78
     factor
    0.75
     berücksichtigen
    0.71
     factores
    0.71
     confounding
    0.71
    Factor
    0.70
     Factor
    0.69
    因素
    0.68
     pesky
    0.68
    Activations Density 2.829%

    No Known Activations