© 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. 91696
    Prev
    Next
    INDEX
    Explanations

    Names and biographical information

    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
    featureID
    -0.81
    ьаж
    -0.81
    脚注の使い方
    -0.78
    SourceChecksum
    -0.77
    LookAnd
    -0.68
     للمعارف
    -0.68
     igjen
    -0.66
    ArrowToggle
    -0.65
    richTextPanel
    -0.64
    kloped
    -0.63
    POSITIVE LOGITS
     propOrder
    0.52
     d
    0.51
     +
    0.47
     encouraging
    0.46
    ,
    0.46
     l
    0.46
     D
    0.45
     kernel
    0.44
     so
    0.43
     encourage
    0.43
    Activations Density 0.006%

    No Known Activations