© 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. 40690
    Prev
    Next
    INDEX
    Explanations

    llis

    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
    IContainer
    -0.63
    UrlResolution
    -0.55
    enumi
    -0.52
    etes
    -0.49
    ducer
    -0.48
    HomeAsUpEnabled
    -0.47
    GOTREF
    -0.46
    Дереккөздер
    -0.45
    logy
    -0.45
     ProtoMessage
    -0.45
    POSITIVE LOGITS
    WriteBarrier
    0.63
    Décès
    0.58
     Tade
    0.58
    tagHelperRunner
    0.56
    ModelBuilder
    0.55
    θει
    0.54
    ViewInit
    0.53
    omości
    0.52
     ◦
    0.52
     arşivlendi
    0.52
    Activations Density 0.063%

    No Known Activations