© 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. 94730
    Prev
    Next
    INDEX
    Explanations

    science/technical

    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
    ########.
    -0.71
    basicConfig
    -0.70
    __(/*!
    -0.69
    LabelTagHelper
    -0.69
    VersionUID
    -0.66
     snippetHide
    -0.66
    ChildScrollView
    -0.64
     HasFactory
    -0.64
    Parcelize
    -0.64
    ReusableCell
    -0.63
    POSITIVE LOGITS
    trab
    0.48
    ục
    0.47
     Liberties
    0.46
    uera
    0.41
     circum
    0.41
    μφ
    0.40
     intptr
    0.40
     Discre
    0.39
     Rechten
    0.39
    [
    0.39
    Activations Density 0.008%

    No Known Activations