© 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. 3572
    Prev
    Next
    INDEX
    Explanations

    general-purpose language

    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
     AssemblyCulture
    -0.94
    
    -0.87
     NSCoder
    -0.80
    findpost
    -0.77
     متعلقه
    -0.75
     doInBackground
    -0.75
     initWithFrame
    -0.72
     ExecuteAsync
    -0.70
    endphp
    -0.69
    новниш
    -0.66
    POSITIVE LOGITS
     Orten
    0.42
    zeiten
    0.41
     volte
    0.40
    ときの
    0.40
    occhio
    0.40
     sendiri
    0.39
    orari
    0.39
     too
    0.39
     names
    0.39
    karni
    0.38
    Activations Density 0.001%

    No Known Activations