© 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. 0-CLT-HP
    7. 93800
    Prev
    Next
    INDEX
    Explanations

    espionage and technology outputs

    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
    Carthy
    -0.49
     Sen
    -0.48
    Outputs
    -0.47
    ATOR
    -0.46
    irement
    -0.45
     mer
    -0.44
    vstack
    -0.44
     myth
    -0.44
    {%
    -0.43
    amia
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.81
     habet
    0.74
     bonté
    0.69
     houſe
    0.68
    exitRule
    0.68
     الحره
    0.67
    ISupport
    0.66
    GenerationType
    0.66
    Datuak
    0.64
     Exacts
    0.64
    Activations Density 0.080%

    No Known Activations