© 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. 0-CLT-HP
    7. 1649
    Prev
    Next
    INDEX
    Explanations

    previous

    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
    previous
    -0.75
     previous
    -0.69
    Previous
    -0.57
    hoeddwyd
    -0.54
     vorige
    -0.52
    tvguidetime
    -0.51
    DebuggerNonUser
    -0.50
     Previous
    -0.48
    GenerationType
    -0.47
    last
    -0.46
    POSITIVE LOGITS
     Egyptians
    0.73
     Italians
    0.71
     Britons
    0.68
     Majefty
    0.67
     villagers
    0.66
     Cubans
    0.66
     barbarians
    0.66
     beings
    0.64
     Varies
    0.64
     puppies
    0.63
    Activations Density 0.125%

    No Known Activations