© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71775
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · 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
    setVerticalGroup
    -0.68
    ConstraintMaker
    -0.65
     GetEnumerator
    -0.61
    SharedDtor
    -0.60
    elemField
    -0.60
    AccessorTable
    -0.60
    !*\
    -0.59
     rospy
    -0.59
    BagLayout
    -0.59
    makeConstraints
    -0.59
    POSITIVE LOGITS
     otomatig
    0.52
    Демографія
    0.49
    been
    0.49
    fin
    0.47
     been
    0.47
     Finn
    0.45
     BEEN
    0.44
     πάνω
    0.43
     finn
    0.43
    Abitanti
    0.42
    Activations Density 0.000%

    No Known Activations