© 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. 77733
    Prev
    Next
    INDEX
    Explanations

    Technical/code language

    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
    ArgsConstructor
    -0.67
     kasarigan
    -0.57
     theory
    -0.53
     Terrasse
    -0.53
    btree
    -0.50
     anta
    -0.50
     employe
    -0.50
    phorus
    -0.49
     Parke
    -0.49
    HasForeignKey
    -0.47
    POSITIVE LOGITS
    TagMode
    0.71
    IContainer
    0.60
     geslacht
    0.60
     XCTest
    0.59
    تقاوى
    0.58
    TypedDataSet
    0.57
    AutoScaleMode
    0.55
    FFIX
    0.54
    esteld
    0.54
    pulumi
    0.51
    Activations Density 0.003%

    No Known Activations