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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38386
    Prev
    Next
    INDEX
    Explanations

    exile

    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
    ="#"><
    -0.45
     suites
    -0.42
     kew
    -0.42
     sketchy
    -0.42
     Zr
    -0.41
    ymce
    -0.41
     عاما
    -0.41
     Pri
    -0.40
     Herz
    -0.40
    prende
    -0.40
    POSITIVE LOGITS
    StoryboardSegue
    0.85
     CreateTagHelper
    0.76
     astore
    0.72
     يتيمه
    0.71
     Baillargeon
    0.71
     שוליים
    0.68
    IsMutable
    0.68
     resourceCulture
    0.68
    bobox
    0.67
     poffible
    0.67
    Activations Density 1.604%

    No Known Activations