© 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. 76272
    Prev
    Next
    INDEX
    Explanations

    Mire

    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
    expandindo
    -0.99
    клопе
    -0.80
    BeginContext
    -0.71
    SourceChecksum
    -0.69
    NewUrlParser
    -0.66
    LabelTagHelper
    -0.65
    ftagPool
    -0.64
     gepubliceerd
    -0.63
    VolleyError
    -0.62
     Exacts
    -0.61
    POSITIVE LOGITS
     inter
    0.65
     naturally
    0.47
    ή
    0.44
     onStart
    0.43
     each
    0.43
     intra
    0.41
    Di
    0.41
     di
    0.41
     epis
    0.41
     semi
    0.40
    Activations Density 0.000%

    No Known Activations