© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 71998
    Prev
    Next
    INDEX
    Explanations

    foreign 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
    LabelTagHelper
    -0.57
    MemoryWarning
    -0.56
    PyTuple
    -0.53
     NSCoder
    -0.53
     wireType
    -0.53
    astify
    -0.50
     vendita
    -0.49
     sabbia
    -0.48
     esprits
    -0.47
    ResponseWriter
    -0.47
    POSITIVE LOGITS
    /***/
    0.53
     stille
    0.52
     FLE
    0.51
     <<<<<<<<<<<<<<
    0.51
    alinga
    0.50
     насељу
    0.48
    Rüyada
    0.48
    Билгалдахарш
    0.47
     uParam
    0.46
    Kjelder
    0.45
    Activations Density 0.001%

    No Known Activations