© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 468
    Prev
    Next
    INDEX
    Explanations

    Title

    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
    tagHelperRunner
    -0.62
    migrationBuilder
    -0.61
    ItemLayout
    -0.58
    MigrationBuilder
    -0.56
    InputBorder
    -0.56
    AddAttribute
    -0.55
     }}"></
    -0.54
     čierna
    -0.54
     Romains
    -0.54
    ----</
    -0.54
    POSITIVE LOGITS
    me
    0.65
     me
    0.57
    lep
    0.51
    '][$
    0.50
    meth
    0.49
     Me
    0.49
    met
    0.48
    bello
    0.47
    Me
    0.47
     para
    0.47
    Activations Density 0.000%

    No Known Activations