© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2970
    Prev
    Next
    INDEX
    Explanations

    Species and geography

    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
    AddColumn
    -0.45
    }],
    -0.44
     gré
    -0.41
    Datuak
    -0.41
     vira
    -0.39
     menyer
    -0.39
     nutz
    -0.39
    ilir
    -0.38
    ⎦
    -0.38
    Namara
    -0.37
    POSITIVE LOGITS
    Personendaten
    0.83
     وتسجيلات
    0.73
    localctx
    0.72
     lenker
    0.71
    ValueStyle
    0.71
    fetchone
    0.69
     CreateTagHelper
    0.65
     nahilalakip
    0.65
    XmlAccessType
    0.63
    KeySpec
    0.63
    Activations Density 0.001%

    No Known Activations