© 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. 0-CLT-HP
    4. 1778
    Prev
    Next
    INDEX
    Explanations

    agawa

    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
     Pan
    -0.75
     hang
    -0.61
     Diagrams
    -0.59
     Diagram
    -0.57
    vician
    -0.53
    liers
    -0.51
    béco
    -0.51
    llon
    -0.50
    Pan
    -0.50
    EndGlobal
    -0.49
    POSITIVE LOGITS
    ftagPool
    0.74
    i
    0.73
     Púb
    0.71
    es
    0.68
    a
    0.66
     pearls
    0.65
    ِّف
    0.64
    ️
    0.60
    ್
    0.60
     propOrder
    0.60
    Activations Density 1.560%

    No Known Activations