© 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. 5-CLT-HP
    7. 6064
    Prev
    Next
    INDEX
    Explanations

    Qualifying 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
    Negative Logits
    LookAnd
    -0.90
     transférez
    -0.73
     <=",
    -0.73
    
    -0.71
    PerformLayout
    -0.70
     transfieras
    -0.70
    InstrumentedTest
    -0.69
     correctes
    -0.65
     Мексичка
    -0.65
     Actual
    -0.64
    POSITIVE LOGITS
    AppCompat
    0.48
    LocalTime
    0.46
    lsa
    0.45
     unusual
    0.43
    })));
    0.43
    Blurb
    0.43
    ]--;
    0.41
     forteller
    0.41
    ον
    0.41
    österreich
    0.40
    Activations Density 0.001%

    No Known Activations