© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 10488
    Prev
    Next
    INDEX
    Explanations

    references to chemical concentrations or levels

    oai_token-act-pair · gpt-4.1-nano
    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
    Negative Logits
    ThroughAttribute
    -0.71
    concentration
    -0.71
     Concentration
    -0.68
     concentration
    -0.68
    LookAnd
    -0.65
    Concentration
    -0.65
    withIdentifier
    -0.60
    тю
    -0.57
    InputBorder
    -0.54
    Stamina
    -0.54
    POSITIVE LOGITS
     concentrations
    1.53
     Concentrations
    1.05
     дописавши
    0.73
    
    0.66
    DidChange
    0.63
    iolis
    0.57
    endphp
    0.56
     αντί
    0.55
    Xna
    0.55
    ñores
    0.55
    Activations Density 0.004%

    No Known Activations