© 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. 1323
    Prev
    Next
    INDEX
    Explanations

    devo

    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
    alus
    -0.86
     grooved
    -0.85
    ildes
    -0.57
    RenderAtEndOf
    -0.51
    Autoritní
    -0.46
     routine
    -0.43
     Karya
    -0.41
     nominate
    -0.40
    posedge
    -0.40
     словарь
    -0.40
    POSITIVE LOGITS
    Captor
    0.72
     ostavi
    0.69
    IUrlHelper
    0.61
     Hiding
    0.60
    rrggbb
    0.60
     anv
    0.59
    Colm
    0.57
     Archiv
    0.57
     Creature
    0.56
    ähteet
    0.56
    Activations Density 1.788%

    No Known Activations