© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 9337
    Prev
    Next
    INDEX
    Explanations

    import

    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
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.81
    ANTLR
    -0.74
     ModelExpression
    -0.70
    tagHelperRunner
    -0.69
     createState
    -0.69
    ::_('
    -0.68
    المناصب
    -0.66
     prom
    -0.64
    Tikang
    -0.64
    ResumeLayout
    -0.63
    POSITIVE LOGITS
     travailleurs
    0.53
     gefü
    0.52
     sauvages
    0.48
     commerciales
    0.47
     affaires
    0.46
     émotions
    0.46
     gagné
    0.46
    WhereInput
    0.45
    GenerationType
    0.45
    ždý
    0.44
    Activations Density 0.833%

    No Known Activations