© 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. 0-CLT-HP
    7. 40534
    Prev
    Next
    INDEX
    Explanations

    0

    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
    IntoConstraints
    -0.64
     noDo
    -0.61
    CppMethod
    -0.59
    PMailer
    -0.59
    IVEREF
    -0.57
     Normdatei
    -0.55
    ValueStyle
    -0.55
    ंदीखरीदारी
    -0.53
    Personendaten
    -0.52
    ьажоргаш
    -0.52
    POSITIVE LOGITS
    1
    1.00
    2
    0.84
    ,
    0.60
    typeparam
    0.57
    0
    0.53
     követ
    0.50
    ,‎
    0.47
    findpost
    0.47
    jandro
    0.46
     rapat
    0.45
    Activations Density 0.160%

    No Known Activations