© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97322
    Prev
    Next
    INDEX
    Explanations

    explaining things

    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
    expandindo
    -0.73
    ParseTree
    -0.64
    mobileqq
    -0.62
     ujednoznacz
    -0.60
     protoimpl
    -0.53
     AssemblyTitle
    -0.51
    ="@+
    -0.51
    them
    -0.50
    Демографія
    -0.50
     него
    -0.48
    POSITIVE LOGITS
     we
    0.92
     humans
    0.69
     humaine
    0.56
     in
    0.56
    humans
    0.55
     humanity
    0.53
     manusia
    0.53
     humaines
    0.52
    onAttach
    0.52
    ису
    0.51
    Activations Density 0.001%

    No Known Activations