© 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. 0-RES-MATRYOSHKA-DC
    7. 11664
    Prev
    Next
    INDEX
    Explanations

    references to quantify the amount of a substance in terms of moles

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.89
     MenuView
    -0.71
    AndEndTag
    -0.69
    脚注の使い方
    -0.65
     Вікі
    -0.63
    Scénario
    -0.62
    DataPropertyName
    -0.61
    хьтан
    -0.60
    RegressionTest
    -0.59
    AutoScaleMode
    -0.59
    POSITIVE LOGITS
    skb
    1.34
    acm
    0.94
     mole
    0.91
    CLR
    0.87
     skb
    0.77
     moles
    0.68
     =&
    0.68
     Mole
    0.66
    vall
    0.64
     actionable
    0.63
    Activations Density 0.016%

    No Known Activations