© 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. 5-CLT-HP
    7. 97272
    Prev
    Next
    INDEX
    Explanations

    Academic/Technical writing

    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
     <=",
    -0.93
     propOrder
    -0.92
     Shakspeare
    -0.85
    windowFixed
    -0.81
    ValueStyle
    -0.81
     Савезне
    -0.79
     Theſe
    -0.79
    berdayakan
    -0.79
    ArrowToggle
    -0.79
     bezeichneter
    -0.78
    POSITIVE LOGITS
     e
    0.55
    e
    0.44
     ir
    0.43
     https
    0.43
    ,
    0.42
     or
    0.42
     this
    0.41
     el
    0.41
     \
    0.41
    মান
    0.40
    Activations Density 0.170%

    No Known Activations