© 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. 5-CLT-HP
    7. 4815
    Prev
    Next
    INDEX
    Explanations

    Dates and references to time

    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
     >=",
    -0.66
     Vikipedi
    -0.66
    parsedMessage
    -0.64
    this
    -0.62
     дописавши
    -0.62
    WriteBarrier
    -0.60
     cherchés
    -0.60
     acestei
    -0.60
    jny
    -0.60
     bezeichneter
    -0.59
    POSITIVE LOGITS
     he
    0.52
    postmedia
    0.47
    קישורים
    0.47
    owar
    0.45
    逅
    0.44
    SequentialGroup
    0.43
     وتسجيلات
    0.43
    iction
    0.42
    SizeF
    0.41
    Бележки
    0.41
    Activations Density 0.004%

    No Known Activations