© 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. 1-CLT-HP
    7. 11580
    Prev
    Next
    INDEX
    Explanations

    ortho

    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
    AndEndTag
    -0.92
    antMatchers
    -0.78
    NameInMap
    -0.69
    MessageOf
    -0.67
    AddTagHelper
    -0.64
    Kariera
    -0.60
     Italijani
    -0.60
    saraba
    -0.60
    ografija
    -0.59
    +#+#
    -0.58
    POSITIVE LOGITS
    \{\\
    0.45
    pae
    0.45
    paf
    0.44
    peti
    0.43
     Pind
    0.43
     préféré
    0.43
     fondé
    0.42
    boer
    0.42
    posti
    0.42
    ãng
    0.42
    Activations Density 0.141%

    No Known Activations