© 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. 175
    Prev
    Next
    INDEX
    Explanations

    scientific research and chemical structures.

    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
     CWE
    -0.52
     placas
    -0.50
     cesse
    -0.50
     otomatig
    -0.49
    pelle
    -0.48
    TimerTask
    -0.48
     fallu
    -0.47
    bootstrapcdn
    -0.47
     administrativa
    -0.47
    хьтан
    -0.47
    POSITIVE LOGITS
     Himo
    0.79
     bond
    0.71
     substitu
    0.69
     ring
    0.68
     bonds
    0.68
     moiety
    0.67
     keten
    0.65
     diha
    0.64
     substituted
    0.60
    Smiles
    0.60
    Activations Density 2.741%

    No Known Activations