© 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. 20-CLT-HP
    7. 78203
    Prev
    Next
    INDEX
    Explanations

    start of new topic

    np_max-act-logits · 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
    Portály
    -0.81
    Personensuche
    -0.75
    UnsafeEnabled
    -0.73
    ⓧ
    -0.71
     rapidity
    -0.69
    '},
    -0.68
     ListTile
    -0.68
    instant
    -0.67
    berdayakan
    -0.66
    ########.
    -0.66
    POSITIVE LOGITS
     with
    0.51
     boldly
    0.42
    forRoot
    0.41
    with
    0.40
    ürlich
    0.38
    With
    0.38
     With
    0.38
     post
    0.37
    ViewImports
    0.37
     ambiti
    0.37
    Activations Density 0.000%

    No Known Activations