© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92889
    Prev
    Next
    INDEX
    Explanations

    Common English connecting words

    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
    ReusableCell
    -0.64
    \{\\
    -0.53
     devriez
    -0.43
    ريقة
    -0.42
     atau
    -0.41
     or
    -0.41
    羹
    -0.40
    koma
    -0.39
     или
    -0.39
    спери
    -0.39
    POSITIVE LOGITS
    <bos>
    1.97
    InjectAttribute
    0.96
    Gambas
    0.93
    oa̍t
    0.90
    RegressionTest
    0.82
     CreateTagHelper
    0.79
     @"/
    0.77
     دیکھیے
    0.76
    Autoritní
    0.75
    ########.
    0.75
    Activations Density 0.160%

    No Known Activations