© 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. 5-CLT-HP
    7. 3718
    Prev
    Next
    INDEX
    Explanations

    math/code

    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
    -0.52
     if
    -0.49
     I
    -0.49
     a
    -0.49
     by
    -0.48
     Y
    -0.48
     so
    -0.47
     given
    -0.46
     on
    -0.46
     Re
    -0.45
    POSITIVE LOGITS
     незавершена
    1.00
    OGND
    0.92
     виправивши
    0.91
    parsedMessage
    0.87
    setVerticalGroup
    0.84
    SharedDtor
    0.82
    AndEndTag
    0.82
     >=",
    0.81
     disambiguazione
    0.81
     &___
    0.80
    Activations Density 0.002%
    No Known Activations