© 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. 5-CLT-HP
    7. 96725
    Prev
    Next
    INDEX
    Explanations

    later

    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
    antMatchers
    -0.69
    findpost
    -0.69
    numerusform
    -0.68
     bezeichneter
    -0.67
     mergeFrom
    -0.66
     ExecuteAsync
    -0.65
     IBOutlet
    -0.63
    featureID
    -0.62
    enumi
    -0.62
    TagMode
    -0.62
    POSITIVE LOGITS
    Last
    0.64
     Last
    0.64
     last
    0.61
     numériques
    0.61
     LAST
    0.52
     últimas
    0.48
     último
    0.48
    last
    0.48
     dernières
    0.47
    Earlier
    0.47
    Activations Density 0.007%

    No Known Activations