© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1427
    Prev
    Next
    INDEX
    Explanations

    without

    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
     having
    -0.95
     taking
    -0.90
     leaving
    -0.86
     making
    -0.85
     creating
    -0.84
     capturing
    -0.83
     getting
    -0.82
     treating
    -0.82
     displaying
    -0.80
     raising
    -0.79
    POSITIVE LOGITS
    hyrchwyd
    0.63
    Бахар
    0.60
     ::=
    0.58
    SharedDtor
    0.58
    μως
    0.57
    archiviato
    0.56
     AssemblyCompany
    0.56
     sumpay
    0.55
     homes
    0.55
    .}\
    0.55
    Activations Density 0.002%

    No Known Activations