© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98210
    Prev
    Next
    INDEX
    Explanations

    math

    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
    ark
    -0.54
     downloader
    -0.52
     ark
    -0.50
    ARK
    -0.50
     synch
    -0.50
    rachtet
    -0.49
    ency
    -0.47
    kenny
    -0.47
    ämpfer
    -0.47
    Mata
    -0.46
    POSITIVE LOGITS
    #)
    0.59
     côtés
    0.56
    harapkan
    0.56
    følgelig
    0.55
     aikaa
    0.52
    DebuggerNonUser
    0.52
    %)
    0.52
    })*/
    0.52
     ellers
    0.52
     isolé
    0.52
    Activations Density 0.040%

    No Known Activations