© 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. 0-CLT-HP
    7. 94152
    Prev
    Next
    INDEX
    Explanations

    technical/medical/introductory language

    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
    rax
    -0.98
    pentine
    -0.91
    obar
    -0.74
    cemia
    -0.53
    ANI
    -0.50
     excision
    -0.49
     mig
    -0.44
    ht
    -0.43
    sste
    -0.42
     vivas
    -0.42
    POSITIVE LOGITS
     resourceCulture
    0.89
    GraphicsUnit
    0.84
     незавершена
    0.84
     Wikimedijinoj
    0.83
     kaarangay
    0.80
    DockStyle
    0.79
    contentLoaded
    0.77
    SourceChecksum
    0.77
    WriteTagHelper
    0.77
    AutoScale
    0.76
    Activations Density 0.093%

    No Known Activations