© 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. 78287
    Prev
    Next
    INDEX
    Explanations

    "esthe"

    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
    tolu
    -0.45
     UIColor
    -0.44
    done
    -0.42
     done
    -0.42
    mern
    -0.41
    mios
    -0.41
    udadera
    -0.41
     Sado
    -0.40
     trocken
    -0.40
    opol
    -0.39
    POSITIVE LOGITS
    esthe
    0.96
    est
    0.93
    este
    0.88
    es
    0.87
    estes
    0.85
    ests
    0.82
    ethe
    0.81
    EST
    0.80
    esthes
    0.79
    esta
    0.77
    Activations Density 0.002%

    No Known Activations