© 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. 1-CLT-HP
    7. 9856
    Prev
    Next
    INDEX
    Explanations

    negation

    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
     jsPsych
    -0.49
    queryInterface
    -0.48
    tagHelperRunner
    -0.47
    VertexArray
    -0.45
     sapore
    -0.44
    gp
    -0.44
    ever
    -0.44
    mtext
    -0.44
    all
    -0.42
    ंदीखरीदारी
    -0.42
    POSITIVE LOGITS
    saraba
    0.68
    posedge
    0.65
    Longueur
    0.64
     HttpNotFound
    0.60
    AutoField
    0.60
    CppCodeGen
    0.60
    expandindo
    0.58
    arbit
    0.57
    ANIEL
    0.57
     bloom
    0.57
    Activations Density 0.021%

    No Known Activations