© 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. 1-RES-MATRYOSHKA-DC
    7. 692
    Prev
    Next
    INDEX
    Explanations

    HTML input elements related to voting or options

    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
     L
    -0.57
    <eos>
    -0.53
     (
    -0.52
    holung
    -0.51
     its
    -0.50
     even
    -0.50
     Sie
    -0.49
    ponse
    -0.48
     the
    -0.48
     fatores
    -0.48
    POSITIVE LOGITS
    Class
    1.56
     Classes
    1.55
     Class
    1.46
    CLASS
    1.38
    Classes
    1.36
     classes
    1.35
     CLASSES
    1.33
     CLASS
    1.31
    class
    1.30
    classes
    1.30
    Activations Density 0.102%

    No Known Activations