© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94076
    Prev
    Next
    INDEX
    Explanations

    adds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.57
     subjects
    -0.54
     ModelRenderer
    -0.53
    ihnachts
    -0.52
     merak
    -0.50
    Handlung
    -0.49
     pinulongan
    -0.49
     FetchType
    -0.48
     SUBJECTS
    -0.48
    subjects
    -0.48
    POSITIVE LOGITS
    awtextra
    0.60
    ècie
    0.53
    protoimpl
    0.52
    oa̍t
    0.52
     <>",
    0.50
    <>();
    0.49
    <>());
    0.47
    iology
    0.47
    ologist
    0.47
    encodeWith
    0.46
    Activations Density 0.004%

    No Known Activations