© 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. 3-RES-MATRYOSHKA-DC
    7. 1779
    Prev
    Next
    INDEX
    Explanations

    words related to metals and chemical compounds

    oai_token-act-pair · gemini-2.0-flash
    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
    migrationBuilder
    -0.82
    urlpatterns
    -0.78
    ieteur
    -0.75
     Coli
    -0.71
     ostavi
    -0.71
    StreetMap
    -0.69
    ImageContext
    -0.69
    MethodManager
    -0.68
     Nark
    -0.68
    potranspiration
    -0.68
    POSITIVE LOGITS
     metal
    2.33
    metal
    2.16
     Metal
    2.14
    Metal
    2.06
     METAL
    2.05
     metals
    1.92
     Metals
    1.80
    METAL
    1.80
     metallic
    1.78
    Metals
    1.72
    Activations Density 0.682%

    No Known Activations