© 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. 5-CLT-HP
    7. 92317
    Prev
    Next
    INDEX
    Explanations

    hypothetical situations

    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
    AddTagHelper
    -1.28
     виправивши
    -1.23
    webElementXpaths
    -1.23
     GenerationType
    -1.18
     propOrder
    -1.13
    AddHtmlAttribute
    -1.13
    LookAnd
    -1.12
    Datuak
    -1.10
    DockStyle
    -1.09
    MigrationBuilder
    -1.09
    POSITIVE LOGITS
    .
    0.56
     and
    0.48
     to
    0.47
     has
    0.41
     करते
    0.39
    ıza
    0.38
     가지
    0.38
     caracteriza
    0.36
     type
    0.36
     under
    0.36
    Activations Density 0.006%

    No Known Activations