© 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. 2757
    Prev
    Next
    INDEX
    Explanations

    bands breaking up/separation

    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
     MainAxisSize
    -0.66
    aarrggbb
    -0.57
    migrationBuilder
    -0.53
     Dank
    -0.51
     oprot
    -0.50
     indexPath
    -0.50
    uarga
    -0.50
     onCancelled
    -0.50
    specialchars
    -0.49
    ├──
    -0.49
    POSITIVE LOGITS
    verwijspagina
    0.55
    曖昧さ回避
    0.53
    rizona
    0.52
     duele
    0.52
    хь
    0.51
    webElementXpaths
    0.50
    WireFormat
    0.50
    ⓘ
    0.48
     Merchandise
    0.48
    gridx
    0.48
    Activations Density 0.001%

    No Known Activations