© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 8998
    Prev
    Next
    INDEX
    Explanations

    virtual

    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
    ViewFeatures
    -0.65
    ioutil
    -0.59
    httphttps
    -0.57
    getahuan
    -0.57
    aarrggbb
    -0.55
    __":
    -0.54
     Egli
    -0.54
    HomeAsUpEnabled
    -0.53
    oa̍t
    -0.53
    '])->
    -0.53
    POSITIVE LOGITS
    κει
    0.57
     Савезне
    0.54
    ///</
    0.50
     correctes
    0.49
    Sqft
    0.47
    olska
    0.47
     ostavi
    0.46
    phrag
    0.45
    voyez
    0.45
     allAfrica
    0.45
    Activations Density 0.013%

    No Known Activations