© 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. 4-CLT-HP
    7. 2755
    Prev
    Next
    INDEX
    Explanations

    to

    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
    alnız
    -0.56
    الحياه
    -0.52
    qrstuvwxyz
    -0.50
    κίνη
    -0.50
    HasOne
    -0.50
    IContainer
    -0.49
     Auge
    -0.49
    IActionResult
    -0.47
     resourceCulture
    -0.47
    ResponseWriter
    -0.46
    POSITIVE LOGITS
     متعلقه
    0.85
    enumi
    0.75
     Normdatei
    0.68
    enumii
    0.67
     head
    0.65
    DoubleQuotes
    0.63
     be
    0.60
    (":");
    0.60
    Bibliograf
    0.58
     esternos
    0.55
    Activations Density 0.003%

    No Known Activations