© 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. 1924
    Prev
    Next
    INDEX
    Explanations

    Slick

    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
     auffi
    -1.37
     myſelf
    -1.30
     juſ
    -1.18
     uſed
    -1.18
     purpoſe
    -1.17
     pleaſure
    -1.17
     ſtate
    -1.16
     ainfi
    -1.16
     ſche
    -1.13
     itſelf
    -1.13
    POSITIVE LOGITS
     In
    1.09
     For
    1.08
     Of
    1.08
     Man
    1.07
     A
    1.04
     L
    1.03
     O
    1.02
     Car
    1.02
     On
    0.99
     To
    0.99
    Activations Density 0.167%

    No Known Activations