© 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. 76277
    Prev
    Next
    INDEX
    Explanations

    Code/foreign words

    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
     تضيفلها
    -0.60
    writeFieldEnd
    -0.59
    CONTRIBUT
    -0.57
    MessageState
    -0.54
    MessageTagHelper
    -0.52
     OMITBAD
    -0.52
    ryu
    -0.51
    tonode
    -0.50
    ant
    -0.50
    MigrationBuilder
    -0.49
    POSITIVE LOGITS
    WriteBarrier
    0.53
    #+#
    0.52
    contentLoaded
    0.51
     externi
    0.50
     autorytatywna
    0.50
    ñores
    0.50
    newBuilder
    0.49
    bezpe
    0.49
     الحره
    0.48
    verwijspagina
    0.48
    Activations Density 0.003%

    No Known Activations