© 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. 12106
    Prev
    Next
    INDEX
    Explanations

    references to specific chemical compounds, particularly choline and molten metal

    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
    rawDesc
    -0.94
     Италијани
    -0.86
    AddHtmlAttribute
    -0.83
     propOrder
    -0.79
    ">//
    -0.79
    Personendaten
    -0.75
    Kaieteur
    -0.74
    Portály
    -0.71
    Portale
    -0.68
    gonic
    -0.67
    POSITIVE LOGITS
    lz
    0.71
    osen
    0.68
     molten
    0.68
    choline
    0.67
    viating
    0.66
     honeycomb
    0.65
    lx
    0.64
     Student
    0.63
    Claude
    0.63
     Students
    0.59
    Activations Density 0.028%

    No Known Activations