© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 469
    Prev
    Next
    INDEX
    Explanations

    unusual word fragments

    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
    <bos>
    -0.57
    jois
    -0.52
    KOM
    -0.50
    routeProvider
    -0.48
    liac
    -0.48
    EntityFramework
    -0.48
    Kom
    -0.48
     Toussaint
    -0.47
    obra
    -0.47
     gon
    -0.47
    POSITIVE LOGITS
     Exactos
    0.62
    sidemargin
    0.56
     fédé
    0.54
    httphttps
    0.54
    bewerken
    0.52
    plevel
    0.51
    schild
    0.50
    neté
    0.50
     jScrollPane
    0.50
    bootstrapcdn
    0.49
    Activations Density 0.026%

    No Known Activations