© 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. 4-CLT-HP
    7. 4803
    Prev
    Next
    INDEX
    Explanations

    data and numbers

    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
    __*/
    -0.56
    RUnlock
    -0.50
    WebServlet
    -0.50
    simplex
    -0.50
     Hệ
    -0.49
    ClCompile
    -0.48
     about
    -0.47
    endswith
    -0.47
    akka
    -0.45
     AppCompat
    -0.45
    POSITIVE LOGITS
    ConstraintMaker
    0.62
     الحره
    0.59
     vomit
    0.57
    jooq
    0.56
    исленность
    0.55
     dump
    0.55
     dumped
    0.54
     and
    0.53
     تضيفلها
    0.51
    DockStyle
    0.51
    Activations Density 0.001%

    No Known Activations