© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1099
    Prev
    Next
    INDEX
    Explanations

    an

    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
     totiž
    -0.63
     nemlig
    -0.57
    󠁢
    -0.55
    どうしても
    -0.52
     namelijk
    -0.52
     dammit
    -0.51
     bowiem
    -0.50
    からです
    -0.50
     nämlich
    -0.49
     purpoſe
    -0.47
    POSITIVE LOGITS
    SharedDtor
    0.75
     entanto
    0.66
    #+#
    0.62
    setVerticalGroup
    0.57
    XmlAccessorType
    0.55
     so
    0.54
    comuna
    0.54
    FileDescriptor
    0.52
    fVar
    0.52
    så
    0.52
    Activations Density 0.021%

    No Known Activations