© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2625
    Prev
    Next
    INDEX
    Explanations

    writing and spelling

    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
    awtextra
    -0.47
     Elephants
    -0.45
     command
    -0.43
     detection
    -0.42
     form
    -0.42
     aste
    -0.42
    لوب
    -0.40
    innen
    -0.39
     Wicidata
    -0.39
    Boats
    -0.39
    POSITIVE LOGITS
     समीक्षक
    0.59
    Abitanti
    0.59
    requireNonNull
    0.56
    çük
    0.55
     remplir
    0.53
     leggi
    0.52
     hende
    0.52
    illère
    0.52
    olino
    0.52
     getItemId
    0.52
    Activations Density 0.001%

    No Known Activations