© 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. 90948
    Prev
    Next
    INDEX
    Explanations

    of in

    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
    XmlAccessorType
    -0.67
     CURIAM
    -0.66
    Personensuche
    -0.60
    GenerationType
    -0.58
    ]")]
    -0.57
    TAINS
    -0.57
    HomeAsUpEnabled
    -0.56
     חיצוניים
    -0.54
     indisponible
    -0.54
     igång
    -0.54
    POSITIVE LOGITS
     this
    0.53
     a
    0.47
    bitat
    0.46
     how
    0.46
    schirm
    0.43
     what
    0.43
    
    0.42
    this
    0.42
     זו
    0.42
     كورة
    0.41
    Activations Density 0.001%

    No Known Activations