© 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. 544
    Prev
    Next
    INDEX
    Explanations

    concentration

    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
    TextHelper
    -0.53
     haza
    -0.51
     تاريخ
    -0.50
     الحره
    -0.50
    GenerationType
    -0.45
    ěn
    -0.45
     NSCoder
    -0.45
    '
    -0.45
     ligiloj
    -0.45
    Patho
    -0.45
    POSITIVE LOGITS
    Personendaten
    0.60
    rrggbb
    0.54
     jadx
    0.53
    FieldBuilder
    0.53
     GoogleFonts
    0.52
     aisladas
    0.52
    NUMX
    0.51
    olated
    0.51
     intention
    0.51
    InputBorder
    0.50
    Activations Density 0.001%

    No Known Activations