© 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. 1-CLT-HP
    7. 9751
    Prev
    Next
    INDEX
    Explanations

    virus

    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
    CodeAttribute
    -0.65
     AssemblyCulture
    -0.54
     réessayer
    -0.53
    arli
    -0.50
     Grüsse
    -0.49
    orsa
    -0.48
    dtd
    -0.47
    poko
    -0.47
     entregó
    -0.46
    setItem
    -0.46
    POSITIVE LOGITS
     rospy
    0.60
    MigrationBuilder
    0.59
    providedIn
    0.59
    AxisAlignment
    0.54
     initComponents
    0.54
     deleteById
    0.51
    writeField
    0.51
     صوتيه
    0.50
    writeFieldEnd
    0.50
    LookAnd
    0.50
    Activations Density 0.028%

    No Known Activations