© 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. 94865
    Prev
    Next
    INDEX
    Explanations

    code and 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
    kháu
    -0.51
    سجيلات
    -0.50
    Said
    -0.48
    قلت
    -0.47
     kjø
    -0.47
     rospy
    -0.47
    ecuted
    -0.46
    sitions
    -0.46
     prochaines
    -0.46
     bière
    -0.46
    POSITIVE LOGITS
    发表于
    0.54
    __":
    0.52
     дописавши
    0.52
    ="@+
    0.50
    __':
    0.50
    ValueGenerated
    0.50
     Romain
    0.50
    AndEndTag
    0.50
     LoggerFactory
    0.49
     ApiException
    0.49
    Activations Density 0.001%

    No Known Activations