© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2511
    Prev
    Next
    INDEX
    Explanations

    scientific/technical documents

    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
     sherds
    -0.74
    AddTagHelper
    -0.72
     itſelf
    -0.72
     Allegretto
    -0.70
     purpoſe
    -0.66
     reaſon
    -0.66
     Jurí
    -0.65
     ſtate
    -0.65
     processions
    -0.64
     secours
    -0.64
    POSITIVE LOGITS
    pushFollow
    0.49
     Leb
    0.44
     Lie
    0.44
    +#+#
    0.44
     TR
    0.44
    GEBURTSDATUM
    0.43
    weebly
    0.42
     potenciales
    0.42
    >(&
    0.41
    trl
    0.41
    Activations Density 0.009%

    No Known Activations