© 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. 12116
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     Philippines
    -0.92
    Philippines
    -0.71
     philippines
    -0.64
    PINES
    -0.64
     Panama
    -0.63
     ModelExpression
    -0.63
     Manila
    -0.59
    Panama
    -0.56
     Panamá
    -0.55
     Solis
    -0.54
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.52
    packing
    0.51
    PyErr
    0.48
    HKEY
    0.47
    chapel
    0.47
     Emir
    0.47
     Arra
    0.47
     OnTriggerEnter
    0.47
    EDEFAULT
    0.47
     Gue
    0.47
    Activations Density 0.007%

    No Known Activations