© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41093
    Prev
    Next
    INDEX
    Explanations

    In

    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
    TagHelpers
    -0.55
     progen
    -0.53
     mitochondria
    -0.50
     acyl
    -0.49
     prophylaxis
    -0.48
    pdev
    -0.48
     nanop
    -0.48
     transmembrane
    -0.48
     etiology
    -0.47
    In
    -0.46
    POSITIVE LOGITS
    tagHelperRunner
    0.74
    utilisons
    0.68
     '\\;'
    0.68
    contentLoaded
    0.66
    lève
    0.66
    <bos>
    0.65
    case
    0.65
     case
    0.65
     Administrativna
    0.64
    Билгалдахарш
    0.63
    Activations Density 0.115%

    No Known Activations