© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 43082
    Prev
    Next
    INDEX
    Explanations

    romic

    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
    romic
    -0.75
     relive
    -0.64
     recreate
    -0.63
     detectors
    -0.59
     nobis
    -0.59
     reluct
    -0.57
     bisous
    -0.57
     Shakspeare
    -0.57
     Maharaja
    -0.56
    PyExc
    -0.56
    POSITIVE LOGITS
    Архівовано
    0.50
    assert
    0.49
    Datagram
    0.48
    idł
    0.47
     Car
    0.46
    aspectj
    0.46
     kasarigan
    0.45
    TagMode
    0.44
    各样的
    0.44
    idosis
    0.43
    Activations Density 0.948%

    No Known Activations