© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 90512
    Prev
    Next
    INDEX
    Explanations

    Geography and locations

    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
     bus
    -0.53
     of
    -0.48
    ...
    -0.47
     hit
    -0.45
     tra
    -0.44
    estacks
    -0.43
     taken
    -0.42
     inter
    -0.42
     formula
    -0.42
     gran
    -0.41
    POSITIVE LOGITS
    GEBURTSDATUM
    0.74
    CloseOperation
    0.73
     Shakspeare
    0.73
    berdayakan
    0.71
    expandindo
    0.70
     Chriftian
    0.69
     Monfieur
    0.69
     démocr
    0.68
    addCriterion
    0.67
     Houſe
    0.67
    Activations Density 0.021%

    No Known Activations