© 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. 94674
    Prev
    Next
    INDEX
    Explanations

    digits

    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
     يتيمه
    -0.66
    })$}
    -0.63
     ***!
    -0.63
    transQ
    -0.61
    lesias
    -0.61
    FormTagHelper
    -0.61
    wixt
    -0.60
    anglès
    -0.57
    principalTable
    -0.57
    ativement
    -0.56
    POSITIVE LOGITS
    ,
    0.64
    AsUp
    0.56
    SharedCtor
    0.52
    <sup>
    0.49
     parere
    0.49
     Tribal
    0.45
     testified
    0.45
    TH
    0.43
     says
    0.43
     TH
    0.43
    Activations Density 0.005%

    No Known Activations