© 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. 91394
    Prev
    Next
    INDEX
    Explanations

    all

    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
     ویکی‌پدی
    -1.04
     kasarigan
    -0.95
    MigrationBuilder
    -0.91
     виправивши
    -0.90
     OFDb
    -0.87
     cherchés
    -0.86
    IVEREF
    -0.85
    SourceChecksum
    -0.85
    Hentet
    -0.84
    homonymie
    -0.82
    POSITIVE LOGITS
     our
    0.57
     the
    0.54
     minute
    0.49
     every
    0.46
    JsonFormat
    0.45
     it
    0.42
     hard
    0.42
    TagHelpers
    0.41
     
    0.40
     of
    0.40
    Activations Density 0.007%

    No Known Activations