© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3848
    Prev
    Next
    INDEX
    Explanations

    hexadecimal code

    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
    iciens
    -0.48
    2
    -0.45
     createState
    -0.44
     K
    -0.43
    lijkse
    -0.42
    K
    -0.41
    writeHead
    -0.41
    NA
    -0.41
    EK
    -0.40
     Glass
    -0.40
    POSITIVE LOGITS
    HasAnnotation
    0.90
    principalColumn
    0.73
    Portale
    0.67
     ExecuteAsync
    0.64
     Roskov
    0.63
    
    0.60
     chré
    0.59
     referrerpolicy
    0.59
    Normdaten
    0.58
    OOTDTY
    0.58
    Activations Density 0.008%

    No Known Activations