© 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. 11880
    Prev
    Next
    INDEX
    Explanations

    references to a specific substance or compound, particularly "lithium."

    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
     EconPapers
    -0.92
    ьаж
    -0.78
     كومونز
    -0.70
    gouv
    -0.69
    zzleHttp
    -0.65
     Syner
    -0.61
    Kaynakça
    -0.61
    новништво
    -0.61
     Syndrome
    -0.59
    tagHelperRunner
    -0.59
    POSITIVE LOGITS
     sy
    2.48
    citep
    0.58
     suck
    0.57
    EVT
    0.57
    曖昧さ回避
    0.56
     ujednoznacz
    0.54
    ECTS
    0.54
    >({
    0.54
    HomeAsUpEnabled
    0.54
    sightly
    0.54
    Activations Density 0.000%

    No Known Activations