© 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. 828
    Prev
    Next
    INDEX
    Explanations

    a

    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
    bootstrapcdn
    -0.75
    MigrationBuilder
    -0.65
    nitř
    -0.59
    uidado
    -0.58
    MockMvc
    -0.57
    ziger
    -0.55
    λευτα
    -0.55
     allAfrica
    -0.54
    utilisons
    -0.54
    setCancelable
    -0.52
    POSITIVE LOGITS
     short
    0.69
     a
    0.62
    short
    0.58
     Short
    0.58
    Short
    0.56
     breve
    0.56
    SHORT
    0.52
    Shorts
    0.52
     profusion
    0.51
     close
    0.50
    Activations Density 0.002%

    No Known Activations