© 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. 1243
    Prev
    Next
    INDEX
    Explanations

    some

    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
     متعلقه
    -0.86
    RegressionTest
    -0.73
    Autoritní
    -0.68
     дописавши
    -0.62
     utafitiHapana
    -0.62
    ніципа
    -0.61
    afficheront
    -0.60
     flesta
    -0.60
     alguno
    -0.59
    أي
    -0.59
    POSITIVE LOGITS
    InstanceState
    0.69
     frequently
    0.63
     helpful
    0.61
     great
    0.61
     common
    0.58
     useful
    0.56
     popular
    0.55
     الوطنيه
    0.55
     commonly
    0.55
     valuable
    0.55
    Activations Density 0.004%

    No Known Activations