© 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. 0-CLT-HP
    7. 42927
    Prev
    Next
    INDEX
    Explanations

    define

    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
     kasarigan
    -0.82
    WebVitals
    -0.74
     AssemblyCulture
    -0.73
     Exacts
    -0.69
    MethodManager
    -0.68
     للاسماء
    -0.66
     houſe
    -0.66
    
    -0.65
     Administrativna
    -0.65
    LookAnd
    -0.63
    POSITIVE LOGITS
    estes
    0.50
     StringBuffer
    0.49
     PROB
    0.49
    chalten
    0.46
    ReadFile
    0.46
     concatenation
    0.46
     var
    0.45
     PREPAR
    0.45
     Displacement
    0.44
     whi
    0.44
    Activations Density 0.817%

    No Known Activations