© 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. 5500
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Према
    -0.67
    Demografía
    -0.62
     متعلقه
    -0.61
     antaranya
    -0.57
    atissimo
    -0.56
    twimg
    -0.56
    ksikon
    -0.54
     esetben
    -0.54
    govina
    -0.53
     opérateur
    -0.53
    POSITIVE LOGITS
     thought
    0.52
     Chwiliwch
    0.48
     Geste
    0.48
     consultato
    0.47
     most
    0.47
     true
    0.47
    ніципалі
    0.47
     THOUGHT
    0.45
     ‘
    0.45
    thought
    0.44
    Activations Density 0.006%

    No Known Activations