© 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. 22-RES-MATRYOSHKA-DC
    7. 753
    Prev
    Next
    INDEX
    Explanations

    a mix of terms used in scientific research papers

    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.22.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.22.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
     becoming
    -0.63
     betraying
    -0.61
     becomes
    -0.53
    xions
    -0.53
     ensuring
    -0.52
     justifying
    -0.51
    raison
    -0.50
     absorbing
    -0.50
     تكون
    -0.49
     Профиль
    -0.49
    POSITIVE LOGITS
    Personendaten
    0.68
     незавершена
    0.66
    InjectAttribute
    0.63
    rungsseite
    0.63
     reduce
    0.61
     REDUC
    0.60
     насељу
    0.58
     améliorer
    0.58
    IUrlHelper
    0.58
     induce
    0.57
    Activations Density 1.061%

    No Known Activations