© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14139
    Prev
    Next
    INDEX
    Explanations

    ballot

    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
     ballot
    -2.03
     Ballot
    -1.67
     ballots
    -1.67
     Ballo
    -1.10
     ballo
    -1.02
    orghini
    -0.60
     BALL
    -0.59
    TagMode
    -0.58
    BALL
    -0.54
    VOTE
    -0.50
    POSITIVE LOGITS
    Билгалдахарш
    0.63
     box
    0.59
    发表于
    0.59
     BOX
    0.58
    setCellValue
    0.56
     BoxDecoration
    0.55
     defaultstate
    0.55
     cellpadding
    0.54
    Box
    0.53
     Box
    0.53
    Activations Density 0.005%

    No Known Activations