© 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. 2867
    Prev
    Next
    INDEX
    Explanations

    server

    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
    IComponent
    -0.66
    KommentareTeilen
    -0.63
    Демографія
    -0.62
     chi̍t
    -0.62
    Autoritní
    -0.59
    AddTagHelper
    -0.54
    DrawerLayout
    -0.53
    AutoScaleMode
    -0.53
    তথ্যসূত্র
    -0.52
    出版年
    -0.51
    POSITIVE LOGITS
    ″]
    0.55
    PositiveButton
    0.54
    }');
    0.51
    '])->
    0.47
     Kama
    0.45
     Besoin
    0.44
    イクアウト
    0.44
    =$?
    0.44
    metheus
    0.43
    ibatis
    0.43
    Activations Density 0.004%

    No Known Activations