© 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. 5-CLT-HP
    7. 764
    Prev
    Next
    INDEX
    Explanations

    Time references

    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
     previously
    -0.71
    はじめに
    -0.70
     earlier
    -0.70
    earlier
    -0.63
     defaultstate
    -0.60
    previously
    -0.59
     yesterday
    -0.59
     anteriormente
    -0.59
     Earlier
    -0.57
    <bos>
    -0.57
    POSITIVE LOGITS
    clerview
    0.54
    ,
    0.54
    raisemb
    0.52
     المعيارى
    0.52
    antaranya
    0.51
    着
    0.51
    — 
    0.50
    ấm
    0.49
    Arbit
    0.48
    ïa
    0.48
    Activations Density 0.002%

    No Known Activations