© 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. 96562
    Prev
    Next
    INDEX
    Explanations

    HTML

    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
     (
    -0.55
    <bos>
    -0.54
     forms
    -0.53
     brethren
    -0.52
    PRO
    -0.52
     moves
    -0.52
    or
    -0.52
     PRO
    -0.51
     towards
    -0.49
     develops
    -0.49
    POSITIVE LOGITS
    TagMode
    0.82
     protoimpl
    0.80
    tagHelperRunner
    0.77
     autorytatywna
    0.75
    RegressionTest
    0.73
    Hochspringen
    0.71
     FetchType
    0.71
    WriteBarrier
    0.70
    orianCalendar
    0.70
    IntoConstraints
    0.69
    Activations Density 0.184%

    No Known Activations