© 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. 16114
    Prev
    Next
    INDEX
    Explanations

    positive

    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
    Negative Logits
     positive
    -1.29
     positifs
    -1.22
    positive
    -1.21
    Positive
    -1.20
     Positive
    -1.18
     POSITIVE
    -1.12
    negative
    -1.05
     negative
    -1.04
     Negative
    -1.04
     positif
    -1.03
    POSITIVE LOGITS
     BoxDecoration
    0.74
     يتيمه
    0.67
    BrowserModule
    0.66
    MLLoader
    0.66
    ChildScrollView
    0.64
    ValueStyle
    0.59
    ModelSerializer
    0.58
    extAlignment
    0.57
    \{\\
    0.57
    ioutil
    0.57
    Activations Density 0.007%

    No Known Activations