© 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. 273
    Prev
    Next
    INDEX
    Explanations

    text related to scientific research with a focus on experiments involving elements and compounds

    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
     onPostExecute
    -0.61
    TagMode
    -0.56
     utafitiHapana
    -0.54
    емость
    -0.53
    емости
    -0.53
    kości
    -0.48
    новништво
    -0.47
    kość
    -0.46
    さっぱり
    -0.46
    tipation
    -0.45
    POSITIVE LOGITS
     exposure
    1.24
    exposure
    1.02
     Exposure
    0.98
     exposures
    0.97
     conditions
    0.95
    Exposure
    0.95
     stimuli
    0.94
     stressors
    0.93
     exposing
    0.91
     environmental
    0.90
    Activations Density 3.763%

    No Known Activations