© 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. 91863
    Prev
    Next
    INDEX
    Explanations

    novel

    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
    AxisAlignment
    -0.70
    IBarButtonItem
    -0.67
     مرئيه
    -0.65
    viewDidLoad
    -0.63
     समीक्षक
    -0.60
    ContentAsync
    -0.58
    MemoryWarning
    -0.57
     aDecoder
    -0.57
     насељу
    -0.57
     pprint
    -0.55
    POSITIVE LOGITS
     legal
    0.54
    ทาง
    0.52
    ery
    0.48
    legal
    0.47
    fjspx
    0.45
     Legal
    0.45
    ERY
    0.44
    gery
    0.44
    Legal
    0.44
    itsky
    0.44
    Activations Density 0.000%

    No Known Activations