© 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. 24-RES-MATRYOSHKA-DC
    7. 921
    Prev
    Next
    INDEX
    Explanations

    concepts of duality and co-existence

    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.24.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.24.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
    awaiter
    -0.54
     próprio
    -0.51
    깥
    -0.50
     dévelo
    -0.48
     dépens
    -0.46
     ioutil
    -0.46
     utanför
    -0.46
    onaceous
    -0.46
     Normdatei
    -0.45
    ValueGeneration
    -0.45
    POSITIVE LOGITS
     together
    1.98
    together
    1.68
    Together
    1.63
     Together
    1.62
     juntos
    1.60
     TOGETHER
    1.54
     mutually
    1.48
     eachother
    1.41
     jointly
    1.40
     elkaar
    1.38
    Activations Density 3.131%

    No Known Activations