© 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. 0-CLT-HP
    4. 92727
    Prev
    Next
    INDEX
    Explanations

    encing

    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
    encing
    -1.44
    clyde
    -1.22
    letal
    -0.66
     
    -0.60
    enced
    -0.58
     C
    -0.52
     bir
    -0.52
     f
    -0.51
     real
    -0.50
     I
    -0.50
    POSITIVE LOGITS
     Efq
    1.12
    IntoConstraints
    1.07
    UrlResolution
    1.02
     myſelf
    1.01
     itſelf
    1.00
     Jefus
    0.99
     doubtnut
    0.98
     purpoſe
    0.97
     Reſ
    0.97
     Anſ
    0.96
    Activations Density 1.652%

    No Known Activations