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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13309
    Prev
    Next
    INDEX
    Explanations

    valently

    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
    valently
    -0.98
    anum
    -0.92
     Roskov
    -0.82
     MessageBoxIcon
    -0.75
    NUMX
    -0.72
     CreateTagHelper
    -0.71
     Савезне
    -0.71
    цездатний
    -0.70
    
    -0.65
    yntaxException
    -0.65
    POSITIVE LOGITS
    XmlRootElement
    0.52
     tapped
    0.46
    topt
    0.45
    vrier
    0.42
     recognized
    0.41
    埔
    0.41
    حوالہ
    0.41
    wira
    0.40
    zku
    0.40
     rela
    0.39
    Activations Density 0.008%

    No Known Activations