© 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. 1-CLT-HP
    7. 11644
    Prev
    Next
    INDEX
    Explanations

    work

    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
     ragaz
    -0.66
     programmation
    -0.61
     oliveira
    -0.60
    ();)
    -0.60
     vérité
    -0.60
     kasarigan
    -0.60
    TagMode
    -0.59
    zilla
    -0.57
    lized
    -0.56
    Ещё
    -0.56
    POSITIVE LOGITS
    fillType
    0.59
     насељу
    0.55
    onViewCreated
    0.54
    !*\
    0.53
    tinyos
    0.51
    FieldBuilder
    0.48
     Мексичка
    0.47
    styleType
    0.45
    Hentet
    0.45
    prepareStatement
    0.45
    Activations Density 0.014%

    No Known Activations