© 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. 0-CLT-HP
    7. 42241
    Prev
    Next
    INDEX
    Explanations

    synthase

    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
    walking
    -0.77
    Walking
    -0.76
     Walking
    -0.76
     CreateTagHelper
    -0.76
    Personensuche
    -0.66
     houſe
    -0.66
    ioutil
    -0.66
     Monfieur
    -0.64
     pleaſure
    -0.63
     Theſe
    -0.63
    POSITIVE LOGITS
    الصفحه
    0.54
    invited
    0.53
    ynx
    0.50
     invited
    0.50
    Massimo
    0.48
    pell
    0.46
     ​​
    0.46
    prnewswire
    0.46
     pres
    0.45
     mas
    0.44
    Activations Density 0.228%

    No Known Activations