© 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. 41900
    Prev
    Next
    INDEX
    Explanations

    NIR

    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
    HAR
    -0.63
    eli
    -0.63
    NIR
    -0.59
    har
    -0.52
    ei
    -0.50
    e
    -0.49
    a
    -0.49
    abe
    -0.48
     har
    -0.47
     And
    -0.46
    POSITIVE LOGITS
     Majefty
    1.12
    ſelf
    0.95
     myſelf
    0.95
     purpoſe
    0.94
     Monfieur
    0.94
     uſed
    0.93
     pleaſure
    0.92
     Theſe
    0.88
     himſelf
    0.86
     itſelf
    0.85
    Activations Density 0.078%

    No Known Activations