© 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. 97792
    Prev
    Next
    INDEX
    Explanations

    important

    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
    tagHelper
    -0.62
    dersfield
    -0.49
    SOUNDBITE
    -0.47
    tér
    -0.47
    ंदीखरीदारी
    -0.46
    tley
    -0.46
     Significance
    -0.45
    Климат
    -0.44
    Significance
    -0.44
    发表于
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    0.72
    LookAnd
    0.72
    moveToFirst
    0.69
    queryInterface
    0.66
    argout
    0.66
     незавершена
    0.66
     linkovi
    0.66
     nahilalakip
    0.63
     WaitForSeconds
    0.63
     ddelweddau
    0.62
    Activations Density 0.001%

    No Known Activations