© 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. 0-CLT-HP
    7. 90438
    Prev
    Next
    INDEX
    Explanations

    together

    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
     together
    -2.47
    together
    -2.31
    Together
    -2.14
     Together
    -2.11
     TOGETHER
    -1.89
     juntos
    -1.78
    gether
    -1.66
     împreună
    -1.63
     вместе
    -1.52
     razem
    -1.49
    POSITIVE LOGITS
    ,
    0.93
    .
    0.66
    ;
    0.60
     -
    0.52
    :
    0.50
     in
    0.49
     (
    0.49
    —
    0.48
    !
    0.48
     against
    0.47
    Activations Density 0.019%

    No Known Activations