© 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. 94325
    Prev
    Next
    INDEX
    Explanations

    packing

    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
     careful
    -0.59
     Careful
    -0.56
     Especially
    -0.54
    Caution
    -0.52
     carefully
    -0.52
     lest
    -0.52
    Achtung
    -0.51
    especially
    -0.51
    Especially
    -0.50
    Careful
    -0.50
    POSITIVE LOGITS
    DockStyle
    0.83
     ModelExpression
    0.80
    styleType
    0.71
    ReusableCell
    0.69
    IndentedString
    0.68
    PageFactory
    0.68
    ✭✭
    0.66
    IntoConstraints
    0.66
    OptionsMenu
    0.64
     protoimpl
    0.63
    Activations Density 0.031%

    No Known Activations