© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10796
    Prev
    Next
    INDEX
    Explanations

    aerospace and military

    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
     HasFactory
    -0.59
    AndEndTag
    -0.53
     kasarigan
    -0.49
     <<<<<<<<<<<<<<
    -0.47
    -------
    -0.46
    
    -0.45
    excellents
    -0.45
    ChatColor
    -0.43
    migrationBuilder
    -0.43
    AutoSize
    -0.43
    POSITIVE LOGITS
    StructEnd
    0.69
    esez
    0.65
    erializer
    0.61
     فريبيس
    0.58
    دانشنامهٔ
    0.57
    modore
    0.55
    ieR
    0.54
    MessageOf
    0.54
     submarines
    0.54
    ότητα
    0.53
    Activations Density 0.009%

    No Known Activations