© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95459
    Prev
    Next
    INDEX
    Explanations

    ton

    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
    ton
    -1.56
    TON
    -1.16
     numbers
    -1.05
    е
    -0.77
     ton
    -0.75
    numbers
    -0.74
     NUMBERS
    -0.67
    Ton
    -0.66
     números
    -0.65
    tons
    -0.64
    POSITIVE LOGITS
    ftagPool
    0.96
    IUrlHelper
    0.88
    ArrowToggle
    0.75
     дописавши
    0.75
     صوتيه
    0.74
    elemField
    0.70
    DebuggerStep
    0.70
    ="@+
    0.69
     surla
    0.68
    ynb
    0.68
    Activations Density 0.130%

    No Known Activations