© 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. 20-CLT-HP
    7. 76888
    Prev
    Next
    INDEX
    Explanations

    Code/variable names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.80
    queryInterface
    -0.79
    tableFuture
    -0.77
    
    -0.77
    RegressionTest
    -0.73
     HasFactory
    -0.71
    LookAnd
    -0.70
     initComponents
    -0.69
    DebuggerNonUser
    -0.66
    !*\
    -0.66
    POSITIVE LOGITS
     ostavi
    0.49
    gyz
    0.47
    bw
    0.46
    AnchorStyles
    0.46
     Pequ
    0.45
    CGRectMake
    0.44
    MATLAB
    0.44
     investigators
    0.44
     backward
    0.43
     PMC
    0.42
    Activations Density 0.000%

    No Known Activations