© 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. 5294
    Prev
    Next
    INDEX
    Explanations

    and

    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
     nagu
    -0.40
     USP
    -0.36
    ResumeLayout
    -0.35
     ويكي
    -0.35
    add
    -0.34
    ADDING
    -0.34
    อย่าง
    -0.34
     بودن
    -0.33
     könnt
    -0.33
    other
    -0.33
    POSITIVE LOGITS
     thicker
    0.87
     brighter
    0.84
     hotter
    0.84
     denser
    0.84
     thinner
    0.84
     darker
    0.83
     bolder
    0.83
     coarser
    0.82
     stronger
    0.82
    leaner
    0.80
    Activations Density 0.001%

    No Known Activations