© 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. 881
    Prev
    Next
    INDEX
    Explanations

    %

    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
    that
    -0.36
    lielmo
    -0.35
    poons
    -0.35
    dass
    -0.35
     lej
    -0.34
     kurz
    -0.33
    ⓘ
    -0.33
    left
    -0.33
    Fel
    -0.33
     patate
    -0.33
    POSITIVE LOGITS
     AssemblyCulture
    0.80
    awtextra
    0.77
     препратки
    0.73
     jsPsych
    0.73
    ThroughAttribute
    0.72
     Walkover
    0.72
     ProtoMessage
    0.69
    AddTagHelper
    0.69
    cetype
    0.68
    ChildScrollView
    0.68
    Activations Density 0.000%

    No Known Activations