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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1080
    Prev
    Next
    INDEX
    Explanations

    code and file paths

    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
    MLLoader
    -0.93
     betweenstory
    -0.88
    NewUrlParser
    -0.86
    ⓧ
    -0.86
    ConstraintMaker
    -0.86
     ProtoMessage
    -0.85
    ressee
    -0.84
     StatefulWidget
    -0.84
    msgTypes
    -0.84
    writeFieldEnd
    -0.82
    POSITIVE LOGITS
    !
    0.44
    /
    0.43
    ala
    0.42
     [
    0.42
    [
    0.42
     [[
    0.41
    .
    0.40
    o
    0.40
     môn
    0.39
    @
    0.38
    Activations Density 0.174%

    No Known Activations