© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13231
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
    стю
    -0.37
    Xna
    -0.36
    går
    -0.33
    randrange
    -0.33
     terceros
    -0.33
    合い
    -0.32
     usus
    -0.32
    anthes
    -0.32
    tagHelper
    -0.31
    canza
    -0.31
    POSITIVE LOGITS
     MainAxisSize
    0.88
    InstrumentedTest
    0.70
    rungsseite
    0.68
    UnsafeEnabled
    0.66
     Meksiku
    0.66
    UnknownFields
    0.66
    SourceChecksum
    0.65
     honed
    0.65
    期刊论文
    0.64
    afficheront
    0.64
    Activations Density 0.048%

    No Known Activations