© 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. 2-RES-MATRYOSHKA-DC
    7. 6069
    Prev
    Next
    INDEX
    Explanations

    mentions of chemical substitution processes

    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
     sub
    -0.65
    entral
    -0.64
    Enlaces
    -0.59
     utafiti
    -0.59
     препратки
    -0.58
    ragen
    -0.57
     cháu
    -0.57
     Oppen
    -0.56
    afficheront
    -0.56
    elemField
    -0.55
    POSITIVE LOGITS
     substituted
    2.38
     substitution
    2.08
     Substitution
    1.94
    substituted
    1.91
     substituting
    1.88
     substitute
    1.84
     substitutions
    1.76
    Substitution
    1.71
    substitute
    1.71
     substitutes
    1.67
    Activations Density 0.017%

    No Known Activations