© 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. 1402
    Prev
    Next
    INDEX
    Explanations

    legal, medical, biochemical

    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
     pleaſure
    -1.22
     ſmall
    -1.15
     Monfieur
    -1.09
     Efq
    -1.05
     greateſt
    -1.04
    o
    -1.04
     houſe
    -1.03
     purpoſe
    -1.03
    y
    -1.03
     ſeveral
    -1.02
    POSITIVE LOGITS
    LookAnd
    0.66
     ur
    0.58
     po
    0.57
    ValueStyle
    0.56
     gynnwys
    0.56
     r
    0.56
     mergeFrom
    0.56
     di
    0.54
    awaiter
    0.53
     Ver
    0.52
    Activations Density 0.093%

    No Known Activations