© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5555
    Prev
    Next
    INDEX
    Explanations

    adverbs

    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
    CloseOperation
    -0.71
     kerap
    -0.71
     usually
    -0.70
     généralement
    -0.69
    #+#
    -0.69
     often
    -0.68
    Often
    -0.67
    often
    -0.65
    usually
    -0.65
     jarang
    -0.63
    POSITIVE LOGITS
    <bos>
    0.57
     Brasileira
    0.54
     TextAppearance
    0.53
     '{@
    0.50
     heard
    0.49
    interopRequire
    0.49
     deduced
    0.48
    ValueStyle
    0.48
     рее
    0.47
     :=
    0.46
    Activations Density 0.006%

    No Known Activations