© 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. 3-RES-MATRYOSHKA-DC
    7. 20
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ing', sometimes with an additional preceding word

    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
    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
     Hornets
    -0.70
     IgE
    -0.70
    ্ন
    -0.69
     getRule
    -0.69
     amizade
    -0.67
     thorax
    -0.66
    acre
    -0.66
    illoma
    -0.66
     коробка
    -0.65
    InstanceState
    -0.65
    POSITIVE LOGITS
    ating
    1.45
    ting
    1.40
    izing
    1.32
    ging
    1.30
    ising
    1.20
    iencing
    1.20
    cting
    1.19
    cing
    1.18
    ning
    1.17
    zing
    1.16
    Activations Density 4.494%

    No Known Activations