© 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. 20-CLT-HP
    7. 73566
    Prev
    Next
    INDEX
    Explanations

    sh

    np_max-act-logits · 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
     estekak
    -0.96
     Audiodateien
    -0.89
    AnchorStyles
    -0.82
    PerformLayout
    -0.81
     linkovi
    -0.79
    ValueStyle
    -0.77
     propOrder
    -0.76
     فريبيس
    -0.75
    posedge
    -0.74
     Taktlose
    -0.74
    POSITIVE LOGITS
     ça
    0.43
    Calling
    0.41
    CDATA
    0.41
     henkil
    0.39
     cal
    0.38
    aldas
    0.38
    rift
    0.37
    дца
    0.37
     coisas
    0.37
    Géographie
    0.36
    Activations Density 0.003%

    No Known Activations