© 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. 0-CLT-HP
    7. 94141
    Prev
    Next
    INDEX
    Explanations

    jumped

    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
     jumps
    -0.65
    ValueStyle
    -0.64
     <<<<<<<<<<<<<<
    -0.62
     pylint
    -0.62
    zz
    -0.62
    MigrationBuilder
    -0.61
     jumped
    -0.61
     giustizia
    -0.60
     leaps
    -0.56
     محفوظة
    -0.55
    POSITIVE LOGITS
     betweenstory
    0.59
    ‍♂️
    0.51
     surla
    0.50
    QObject
    0.48
    awm
    0.48
    Портал
    0.48
    ancial
    0.47
     Arjuna
    0.47
    IsMutable
    0.47
     Pologne
    0.46
    Activations Density 0.045%

    No Known Activations