© 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. 73130
    Prev
    Next
    INDEX
    Explanations

    Technical/Academic text

    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
    PerformLayout
    -0.80
    Autoritní
    -0.68
     esternos
    -0.65
    stateProvider
    -0.63
    featureID
    -0.60
    GEBURTSDATUM
    -0.59
     Administrativna
    -0.59
    oredCriteria
    -0.59
    횟
    -0.57
     odkazy
    -0.57
    POSITIVE LOGITS
    หน่อย
    0.47
    ########.
    0.47
    ApiClient
    0.47
     समीक्षाओं
    0.44
    basicConfig
    0.44
    AnchorStyles
    0.44
    verket
    0.43
     getSub
    0.43
     MaterialApp
    0.43
    QUET
    0.42
    Activations Density 0.011%

    No Known Activations