© 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. 0-CLT-HP
    7. 91963
    Prev
    Next
    INDEX
    Explanations

    Middle-Eastern countries

    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
     Syrian
    -0.82
    はじめに
    -0.67
     driveway
    -0.61
    s
    -0.60
    .(*
    -0.58
     @"/
    -0.56
    skraft
    -0.56
    iParam
    -0.55
    CompilerServices
    -0.55
    клопе
    -0.54
    POSITIVE LOGITS
    VersionUID
    0.66
    hobo
    0.54
    enumii
    0.51
    RequestMethod
    0.50
     aba
    0.49
     ProtoMessage
    0.49
    webtoken
    0.49
    reuung
    0.49
    luck
    0.48
    maids
    0.48
    Activations Density 0.083%

    No Known Activations