© 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. 1-CLT-HP
    4. 45984
    Prev
    Next
    INDEX
    Explanations

    than

    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
    enumi
    -0.54
    تقاوى
    -0.52
     devront
    -0.50
    Numerology
    -0.48
     privadas
    -0.46
    begin
    -0.45
     responsabilità
    -0.45
    ta
    -0.44
     mẹ
    -0.44
     olduğunu
    -0.43
    POSITIVE LOGITS
    httphttps
    0.75
    APORE
    0.66
    AddTagHelper
    0.64
     HasFactory
    0.63
     tartalomajánló
    0.63
    NUMX
    0.60
    Composable
    0.60
    日閲覧
    0.59
     indisponible
    0.57
     BOT
    0.57
    Activations Density 0.031%

    No Known Activations