© 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. 1-CLT-HP
    7. 11444
    Prev
    Next
    INDEX
    Explanations

    immun

    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
     سكانية
    -0.69
    parsedMessage
    -0.69
     poffe
    -0.65
     Chwiliwch
    -0.65
    hyrchwyd
    -0.65
     fubject
    -0.64
     externi
    -0.64
    OGND
    -0.63
     preſent
    -0.63
     satisfied
    -0.62
    POSITIVE LOGITS
    ology
    0.60
    olo
    0.52
    ologic
    0.50
    ologically
    0.49
     ujednoznacz
    0.45
    izing
    0.45
    ič
    0.44
    vč
    0.44
    omo
    0.43
    vägen
    0.43
    Activations Density 0.038%

    No Known Activations