© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71487
    Prev
    Next
    INDEX
    Explanations

    Technical language/code

    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
    Negative Logits
    TagHelper
    -0.63
    migrationBuilder
    -0.61
     Ababa
    -0.60
     surla
    -0.60
     يتيمه
    -0.57
     Jue
    -0.55
    CppCodeGen
    -0.54
    CreateModel
    -0.54
    Literatur
    -0.52
    contentLoaded
    -0.52
    POSITIVE LOGITS
     Clos
    0.48
    MultipartFile
    0.45
    #+#
    0.45
    FieldBuilder
    0.44
    addCriterion
    0.43
     ***!
    0.42
    newInstance
    0.41
     BorderSide
    0.41
    WithIOException
    0.40
    Atoi
    0.40
    Activations Density 0.002%

    No Known Activations