© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 92707
    Prev
    Next
    INDEX
    Explanations

    Naval 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
    脚注の使い方
    -0.74
    bili
    -0.67
    AndEndTag
    -0.65
    Diwedd
    -0.62
    IUrlHelper
    -0.62
    contentLoaded
    -0.60
     дописавши
    -0.60
    bitField
    -0.59
    IsContent
    -0.58
    XMLSchema
    -0.58
    POSITIVE LOGITS
    vety
    0.66
    antasy
    0.57
    e
    0.57
    eled
    0.54
    alty
    0.51
    ed
    0.50
     PublicKey
    0.49
    s
    0.48
    BIND
    0.47
    }]
    
    0.46
    Activations Density 1.602%

    No Known Activations