© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2491
    Prev
    Next
    INDEX
    Explanations

    bow

    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
    UnsafeEnabled
    -0.60
     Morena
    -0.59
     awaits
    -0.58
     لينك
    -0.57
     Ouro
    -0.57
     awaited
    -0.54
     Sino
    -0.53
    TagHelper
    -0.53
    rim
    -0.53
     NOL
    -0.53
    POSITIVE LOGITS
     fieldNum
    0.61
    Revenir
    0.50
     Wicidata
    0.50
    AutoresizingMask
    0.47
    Ự
    0.46
    Personendaten
    0.46
     Bioaccumulative
    0.44
    PyExc
    0.44
    ellees
    0.42
     Assignee
    0.41
    Activations Density 0.001%

    No Known Activations