© 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. 402
    Prev
    Next
    INDEX
    Explanations

    mina

    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
     '\\;'
    -0.70
    новништво
    -0.52
    ChildScrollView
    -0.48
    getSupport
    -0.47
    atsen
    -0.47
     Infor
    -0.46
    Genie
    -0.45
     ROB
    -0.45
    ClientRect
    -0.44
     inappropriés
    -0.44
    POSITIVE LOGITS
    mybatisplus
    0.73
    NameInMap
    0.65
    #+#
    0.63
    IUrlHelper
    0.61
    Geplaatst
    0.61
    enumii
    0.60
    querque
    0.57
     متعلقه
    0.57
     насељу
    0.54
     numberWith
    0.54
    Activations Density 0.005%

    No Known Activations