© 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. 20-CLT-HP
    7. 75688
    Prev
    Next
    INDEX
    Explanations

    code/technical language

    np_max-act-logits · 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
     bb
    -0.61
    bB
    -0.60
    rrggbb
    -0.60
    STRACT
    -0.55
     Fath
    -0.54
    miral
    -0.54
    xase
    -0.53
     abb
    -0.52
    μαι
    -0.52
    Refrain
    -0.52
    POSITIVE LOGITS
    webElementXpaths
    0.53
     EconPapers
    0.48
     onPostExecute
    0.48
    SPATH
    0.47
    RegistryLite
    0.46
    P
    0.46
     PO
    0.44
    zieren
    0.44
     DBNull
    0.43
     P
    0.42
    Activations Density 0.001%

    No Known Activations